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

    Neuronpedia

    INDEX
    Explanations

    secrets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getMonth
    -0.07
     Google
    -0.07
    GetMethod
    -0.06
     zza
    -0.06
    "]))
    -0.06
    ้าก
    -0.06
     �
    -0.06
    (value
    -0.06
    .nn
    -0.06
     teammates
    -0.06
    POSITIVE LOGITS
     use
    0.07
    iting
    0.06
    тал
    0.06
     mechanisms
    0.06
     employ
    0.06
     discoveries
    0.06
    _ber
    0.06
     perpetrator
    0.06
    -license
    0.06
     programmed
    0.06
    Act Density 0.035%

    No Known Activations