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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pesticides
    -0.07
    dbContext
    -0.06
    .trip
    -0.06
     jq
    -0.06
    ası
    -0.06
    _registers
    -0.06
    람
    -0.06
     (**
    -0.06
     Hakk
    -0.06
    olders
    -0.06
    POSITIVE LOGITS
    移到
    0.07
     learning
    0.07
    Much
    0.06
     combust
    0.06
     متفاوت
    0.06
     практически
    0.06
     Cert
    0.06
    	AND
    0.06
    genden
    0.06
    classify
    0.06
    Act Density 0.000%

    No Known Activations