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

    Neuronpedia

    INDEX
    Explanations

    -like

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yatırım
    -0.07
     Biden
    -0.06
    \Security
    -0.06
     Idol
    -0.06
     информации
    -0.06
     rebounds
    -0.06
     kancel
    -0.06
     Boehner
    -0.06
     ourselves
    -0.06
     tasarım
    -0.06
    POSITIVE LOGITS
    similar
    0.09
    ashire
    0.08
    ish
    0.07
    -like
    0.07
    _le
    0.06
    iform
    0.06
    허
    0.06
     /*<<<
    0.06
     형
    0.06
     elif
    0.06
    Act Density 0.014%

    No Known Activations