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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sam
    -0.08
     das
    -0.08
    :b
    -0.08
    ⓢ
    -0.07
    .tbl
    -0.07
     tag
    -0.07
     Barrel
    -0.07
     Super
    -0.07
     Such
    -0.07
     solicitud
    -0.07
    POSITIVE LOGITS
     Telegraph
    0.07
    �
    0.07
    إدار
    0.06
     unn
    0.06
    🍁
    0.06
    乐团
    0.06
    �
    0.06
    _AI
    0.06
    (MenuItem
    0.06
    工商联
    0.06
    Act Density 0.017%

    No Known Activations