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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dedication or focus towards specific causes or topics

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

    dedicated to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumii
    -0.52
    期刊论文
    -0.48
    VYMaps
    -0.43
     Roskov
    -0.41
    atelli
    -0.40
     Simult
    -0.40
     cime
    -0.40
    ፩
    -0.39
     Baskets
    -0.37
    Essays
    -0.37
    POSITIVE LOGITS
    Cyfeiriadau
    0.53
    EndInit
    0.43
    RTGC
    0.42
    PerformLayout
    0.42
     dedicado
    0.41
     dédiée
    0.41
     dedicada
    0.40
     listo
    0.39
    setVerticalGroup
    0.39
     encargada
    0.39
    Act Density 0.221%

    No Known Activations