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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Belize
    -0.07
     تأ
    -0.07
     žalob
    -0.06
     alanda
    -0.06
     equipo
    -0.06
     kurtul
    -0.06
    porno
    -0.06
    aptors
    -0.06
    ildiği
    -0.06
     Byl
    -0.06
    POSITIVE LOGITS
    :n
    0.06
     Roch
    0.06
    服
    0.06
    َر
    0.06
    运
    0.06
    	LP
    0.06
     INPUT
    0.06
    _metric
    0.06
    Env
    0.06
    .DATA
    0.06
    Act Density 0.004%

    No Known Activations