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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raspberry
    -0.07
     Townsend
    -0.07
     kazan
    -0.06
    lane
    -0.06
     withStyles
    -0.06
    ěla
    -0.06
     banana
    -0.06
    .interpolate
    -0.06
     Brend
    -0.06
    methodName
    -0.06
    POSITIVE LOGITS
     �
    0.07
    azu
    0.06
     кисл
    0.06
    gies
    0.06
    GE
    0.06
    	rb
    0.06
    ersive
    0.06
     isr
    0.06
    _MODAL
    0.06
     hissed
    0.06
    Act Density 0.002%

    No Known Activations