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

    Neuronpedia

    INDEX
    Explanations

    weapons and violence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     studying
    -0.07
    앤
    -0.06
     Kut
    -0.06
    確認
    -0.06
    eacher
    -0.06
    .authentication
    -0.06
    exp
    -0.06
    ская
    -0.06
    Scanner
    -0.06
    _ttl
    -0.06
    POSITIVE LOGITS
    Inventory
    0.07
    Boot
    0.07
    ;line
    0.07
    'ye
    0.06
    plash
    0.06
    rej
    0.06
    _Blue
    0.06
     Alonso
    0.06
    enerative
    0.06
    _pm
    0.06
    Act Density 0.225%

    No Known Activations