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

    Neuronpedia

    INDEX
    Explanations

    narrative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FileAccess
    -0.07
    وئ
    -0.07
    _last
    -0.07
     Cognitive
    -0.07
     rated
    -0.07
     twins
    -0.06
     Wiring
    -0.06
    _AC
    -0.06
     før
    -0.06
     nave
    -0.06
    POSITIVE LOGITS
    appName
    0.07
     nghi
    0.07
    [%
    0.06
    /lab
    0.06
    }">↵
    0.06
    -equiv
    0.06
    icked
    0.06
     Simmons
    0.06
     ENC
    0.06
    igslist
    0.06
    Act Density 0.269%

    No Known Activations