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

    Neuronpedia

    INDEX
    Explanations

    capture, imprisonment, misfortune

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rhetorical
    -0.06
     blí
    -0.06
    лоч
    -0.06
    _extraction
    -0.06
     Chancellor
    -0.06
     Eva
    -0.06
     GTK
    -0.06
    eneral
    -0.06
     philosophical
    -0.06
     MOZ
    -0.06
    POSITIVE LOGITS
    飞
    0.07
     pem
    0.07
     agent
    0.07
     omas
    0.06
    ##_
    0.06
    .legend
    0.06
     giov
    0.06
     difficile
    0.06
    imiter
    0.06
    _ORDER
    0.06
    Act Density 0.057%

    No Known Activations