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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vive
    -0.07
     Cities
    -0.07
     Cyc
    -0.06
     classify
    -0.06
    bian
    -0.06
     triangular
    -0.06
    ''
    -0.06
    Expand
    -0.06
     denial
    -0.06
     Paran
    -0.06
    POSITIVE LOGITS
     immediately
    0.08
     must
    0.07
    iosk
    0.07
     Barrett
    0.07
     لر
    0.07
     but
    0.07
    buffer
    0.07
     But
    0.07
     showDialog
    0.07
    0.07
    Act Density 0.003%

    No Known Activations