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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    משכנת
    -0.07
    ENN
    -0.07
    uro
    -0.07
    🍽
    -0.06
    UEST
    -0.06
    飲
    -0.06
     horm
    -0.06
     Bios
    -0.06
    ��
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Twitter
    0.07
    (process
    0.07
    𝐞
    0.07
     sidebar
    0.07
    -wrap
    0.07
     życie
    0.07
    _HandleTypeDef
    0.07
    夜里
    0.07
     bigotry
    0.07
    _actions
    0.06
    Act Density 0.001%

    No Known Activations