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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     icon
    -0.07
    ida
    -0.07
     swims
    -0.07
     Floyd
    -0.06
    irms
    -0.06
     succeed
    -0.06
    ICT
    -0.06
    steller
    -0.06
    	handler
    -0.06
    Exit
    -0.06
    POSITIVE LOGITS
    .getStyle
    0.06
     ผล
    0.06
    地球
    0.06
    .el
    0.06
    <message
    0.06
     Proble
    0.06
     пят
    0.06
    memcmp
    0.06
    _TILE
    0.06
     UNU
    0.06
    Act Density 0.016%

    No Known Activations