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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison and evaluation

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

    that follow "to"

    np_acts-logits-general · gemini-2.0-flash

    infinitive verb constructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ˌ
    -0.31
    larak
    -0.27
    ваясь
    -0.27
     pasos
    -0.27
     avoided
    -0.26
     mahd
    -0.25
    garek
    -0.25
    tableFuture
    -0.24
     vidi
    -0.24
    今後の
    -0.24
    POSITIVE LOGITS
     Signalez
    0.64
     שוליים
    0.63
    AddTagHelper
    0.63
     Infórmanos
    0.62
    tamaris
    0.58
    ⓧ
    0.58
     nahilalakip
    0.57
    pencer
    0.56
     ſei
    0.56
    niſſe
    0.55
    Act Density 0.346%

    No Known Activations