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

    Neuronpedia

    INDEX
    Explanations

    occurrences of directed actions or interactions involving individuals

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

    direction or movement

    np_acts-logits-general · gemini-2.0-flash

    direction at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.52
     ſtre
    -0.50
    idah
    -0.48
    atos
    -0.48
    bootstrapcdn
    -0.48
     preſent
    -0.47
    ')}
    -0.47
     marginLeft
    -0.47
    "){
    -0.47
     kinematics
    -0.46
    POSITIVE LOGITS
     propOrder
    0.81
     direction
    0.73
    fjspx
    0.72
     للاسماء
    0.69
    expandindo
    0.67
     DIRECTION
    0.66
    direction
    0.65
     my
    0.65
    LookAnd
    0.64
    FunctionFlags
    0.63
    Act Density 0.087%

    No Known Activations