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

    Neuronpedia

    INDEX
    Explanations

    say punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     כל
    -0.07
    亳
    -0.07
     Hindi
    -0.07
     cigar
    -0.07
     KO
    -0.06
     File
    -0.06
     والف
    -0.06
    -Qaeda
    -0.06
     disciplined
    -0.06
     biç
    -0.06
    POSITIVE LOGITS
    athers
    0.07
    ACCESS
    0.07
     acknowledged
    0.07
    很不错
    0.07
     Soc
    0.07
     RESPONSE
    0.07
     comm
    0.07
     Resort
    0.07
    でしょうか
    0.07
     Datensch
    0.07
    Act Density 0.026%

    No Known Activations