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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิงห
    -0.07
    itizer
    -0.06
     outline
    -0.06
     Shim
    -0.06
    Hel
    -0.06
    Native
    -0.06
    .DataGridViewColumn
    -0.06
    _LOADING
    -0.06
     Ket
    -0.06
     Pant
    -0.06
    POSITIVE LOGITS
    addComponent
    0.07
    عام
    0.07
     evasion
    0.07
     Hannah
    0.07
     Salman
    0.07
    /octet
    0.06
    Excellent
    0.06
     чуть
    0.06
     #-}↵↵
    0.06
    role
    0.06
    Act Density 0.009%

    No Known Activations