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

    Neuronpedia

    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ew
    -0.07
     infuri
    -0.07
     jednodu
    -0.06
     ctype
    -0.06
    ymce
    -0.06
    dojo
    -0.06
     riots
    -0.06
    seudo
    -0.06
     уров
    -0.06
    واهد
    -0.06
    POSITIVE LOGITS
     gaze
    0.07
    	draw
    0.07
    liers
    0.07
     роз
    0.06
     Pacers
    0.06
    -bot
    0.06
    -ignore
    0.06
    ندا
    0.06
    dismiss
    0.06
    _host
    0.06
    Act Density 0.000%

    No Known Activations