Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    actions involving projectiles or thrown objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Motion or direction, often involving throwing

    np_acts-logits-general · gemini-2.0-flash

    throwing things at or towards something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posedge
    -0.60
     gynhyrchwyd
    -0.59
    ArgumentParser
    -0.59
    "){
    -0.56
    tahui
    -0.56
     GenerationType
    -0.55
    gency
    -0.55
    bigr
    -0.55
     (;;)
    -0.54
    JOUR
    -0.53
    POSITIVE LOGITS
     at
    0.94
     towards
    0.92
     toward
    0.90
    toward
    0.78
    towards
    0.77
     directed
    0.71
     richting
    0.70
     Towards
    0.69
    Towards
    0.67
     Richtung
    0.64
    Act Density 0.115%

    No Known Activations