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

    Neuronpedia

    INDEX
    Explanations

    running/management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    armor
    -0.06
     sacram
    -0.06
     Anti
    -0.06
     الثاني
    -0.06
     Voldemort
    -0.06
    wo
    -0.06
     �
    -0.06
    eneg
    -0.06
     deposits
    -0.05
    आई
    -0.05
    POSITIVE LOGITS
    Never
    0.07
    .times
    0.07
    Shutdown
    0.07
     사항
    0.07
    orElse
    0.07
     patiently
    0.07
    inou
    0.07
    cent
    0.07
    Director
    0.06
    AuthProvider
    0.06
    Act Density 0.052%

    No Known Activations