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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ampl
    -0.07
    Merge
    -0.06
     glasses
    -0.06
     juste
    -0.06
    冲
    -0.06
    .ant
    -0.06
     softly
    -0.06
     Differential
    -0.06
     beams
    -0.06
     پرداخت
    -0.06
    POSITIVE LOGITS
     wal
    0.07
    tls
    0.06
     ban
    0.06
     şey
    0.06
     Tek
    0.06
     đàn
    0.06
    시아
    0.06
    383
    0.06
     πρω
    0.06
     Trout
    0.06
    Act Density 0.051%

    No Known Activations