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

    Neuronpedia

    INDEX
    Explanations

    accidents and injuries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ()->
    -0.07
     рассчит
    -0.07
     brut
    -0.06
     recursive
    -0.06
     obsessive
    -0.06
     anlamda
    -0.06
    Conversion
    -0.06
     ترجم
    -0.06
    883
    -0.06
     foresee
    -0.06
    POSITIVE LOGITS
     eman
    0.07
    INAL
    0.07
     poop
    0.06
    -grow
    0.06
     booty
    0.06
    !)↵↵
    0.06
    element
    0.06
    _capabilities
    0.06
     ego
    0.06
     torino
    0.06
    Act Density 0.029%

    No Known Activations