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

    Neuronpedia

    INDEX
    Explanations

    ical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bows
    -0.06
     hates
    -0.06
    .execution
    -0.06
    genus
    -0.06
    metry
    -0.06
     fend
    -0.06
    .warning
    -0.06
    aremos
    -0.06
    Proxy
    -0.06
    زارش
    -0.05
    POSITIVE LOGITS
     Perth
    0.06
    concert
    0.06
     Clarkson
    0.06
    'Neill
    0.06
     _____
    0.06
     Listener
    0.06
     subway
    0.06
     تسم
    0.06
     Turner
    0.06
    حل
    0.06
    Act Density 0.000%

    No Known Activations