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

    Neuronpedia

    INDEX
    Explanations

    iPhones and phones

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	angle
    -0.07
     Lotto
    -0.07
    _anim
    -0.07
    _th
    -0.07
    ेस
    -0.06
    _cent
    -0.06
    notif
    -0.06
    號
    -0.06
    hyth
    -0.06
     Ecology
    -0.06
    POSITIVE LOGITS
     dramatically
    0.07
     ξ
    0.07
     trainer
    0.07
     quanto
    0.06
     Arguments
    0.06
    vla
    0.06
     sanit
    0.06
     návr
    0.06
     Youtube
    0.06
     -↵
    0.06
    Act Density 0.043%

    No Known Activations