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

    Neuronpedia

    INDEX
    Explanations

    radio

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Addiction
    -0.07
    -story
    -0.07
     Chevy
    -0.06
     чт
    -0.06
     П
    -0.06
     From
    -0.06
     easier
    -0.06
    from
    -0.06
     dirty
    -0.06
    以下
    -0.06
    POSITIVE LOGITS
    sembly
    0.07
     jButton
    0.07
     onResponse
    0.06
    긔
    0.06
     peach
    0.06
    .ax
    0.06
    址
    0.06
    AJOR
    0.06
    .withOpacity
    0.06
     colomb
    0.06
    Act Density 0.002%

    No Known Activations