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

    Neuronpedia

    INDEX
    Explanations

    aggressive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     요
    -0.08
     minus
    -0.06
     rn
    -0.06
    anik
    -0.06
    .TEXTURE
    -0.06
     Castle
    -0.06
     ruins
    -0.06
     owed
    -0.06
    _PHONE
    -0.06
     buying
    -0.06
    POSITIVE LOGITS
     aggressive
    0.11
     salope
    0.08
     arrog
    0.08
     vigorously
    0.08
     aggressively
    0.07
     inefficient
    0.07
     Rapid
    0.07
    (MSG
    0.07
     actively
    0.07
    feas
    0.07
    Act Density 0.008%

    No Known Activations