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

    Neuronpedia

    INDEX
    Explanations

    request

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Strings
    -0.06
    yte
    -0.06
    .handleClick
    -0.06
    ouch
    -0.06
    ा�
    -0.06
    .Command
    -0.06
    stm
    -0.06
    astic
    -0.06
     hinges
    -0.06
     Do
    -0.06
    POSITIVE LOGITS
     offence
    0.07
     δυ
    0.07
     sell
    0.06
    gambar
    0.06
     fascinated
    0.06
     đủ
    0.06
    //#
    0.06
     slippery
    0.06
    _cate
    0.06
     fastball
    0.06
    Act Density 0.009%

    No Known Activations