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

    Neuronpedia

    INDEX
    Explanations

    hazard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Up
    -0.07
    Telefone
    -0.07
    ьому
    -0.07
    従
    -0.07
    .RelativeLayout
    -0.07
    三年
    -0.07
     segundo
    -0.07
    /png
    -0.07
    Vy
    -0.07
    えて
    -0.06
    POSITIVE LOGITS
     hazard
    0.14
     Hazard
    0.13
     hazards
    0.12
     hazardous
    0.09
    azard
    0.08
     capitalize
    0.07
     Haz
    0.07
     wasted
    0.07
    hover
    0.07
    Handler
    0.07
    Act Density 0.004%

    No Known Activations