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

    Neuronpedia

    INDEX
    Explanations

    giant, compensate, friends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     અનુ
    0.40
    listView
    0.38
     справи
    0.38
    Droite
    0.38
     unattractive
    0.38
    వారం
    0.37
    чёт
    0.37
     reunião
    0.37
    视图
    0.37
    सूची
    0.36
    POSITIVE LOGITS
     agon
    0.41
     giants
    0.41
     giant
    0.41
    idze
    0.40
     Goliath
    0.39
    巨
    0.38
     Mn
    0.38
     objc
    0.38
     funk
    0.38
     Hz
    0.38
    Act Density 0.001%

    No Known Activations