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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     country
    -0.07
    bish
    -0.07
    razy
    -0.07
     Slo
    -0.06
     παιδ
    -0.06
     راه
    -0.06
     cultural
    -0.06
     PrintWriter
    -0.06
     antivirus
    -0.06
     giorno
    -0.06
    POSITIVE LOGITS
     tenure
    0.07
    ेवल
    0.06
     AND
    0.06
    čky
    0.06
    TRGL
    0.06
    <AudioSource
    0.06
    .ActionBar
    0.06
    imdi
    0.06
    .Env
    0.06
    _POSTFIELDS
    0.06
    Act Density 0.006%

    No Known Activations