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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bad
    -0.07
    elier
    -0.07
    iks
    -0.07
     dies
    -0.06
     Joan
    -0.06
     Lydia
    -0.06
    μένα
    -0.06
    ούν
    -0.06
    Prof
    -0.06
    CPF
    -0.06
    POSITIVE LOGITS
    _GUID
    0.07
    ichten
    0.07
     rep
    0.06
     Variable
    0.06
    _latency
    0.06
     colorWithRed
    0.06
    >'.$
    0.06
    .SEVER
    0.06
    .pull
    0.06
     agree
    0.06
    Act Density 0.008%

    No Known Activations