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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -budget
    -0.07
     existence
    -0.07
     reloading
    -0.07
    abyte
    -0.06
    γραφ
    -0.06
    inson
    -0.06
     thư
    -0.06
     vestib
    -0.06
     bilim
    -0.06
     jew
    -0.06
    POSITIVE LOGITS
    _start
    0.06
    they
    0.06
    �
    0.06
    ｨ
    0.06
    .LookAndFeel
    0.06
     jac
    0.06
    okable
    0.06
     RECT
    0.06
    oolStrip
    0.06
    گوی
    0.06
    Act Density 0.000%

    No Known Activations