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

    Neuronpedia

    INDEX
    Explanations

    Web page excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thirsty
    -0.08
     Naughty
    -0.07
    .tr
    -0.07
     twisted
    -0.06
     dequeueReusableCellWithIdentifier
    -0.06
    ตะ
    -0.06
    Difficulty
    -0.06
     �
    -0.06
    State
    -0.06
     Fruit
    -0.06
    POSITIVE LOGITS
     newState
    0.07
    од
    0.06
     bombers
    0.06
    folder
    0.06
     stranded
    0.06
     действия
    0.06
    userName
    0.06
     strapon
    0.06
     Promo
    0.06
    multipart
    0.06
    Act Density 0.032%

    No Known Activations