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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DR
    -0.07
    YSTICK
    -0.06
     thugs
    -0.06
     بزر
    -0.06
    Skipping
    -0.06
    peech
    -0.06
    testimonial
    -0.06
     veterans
    -0.06
    خو
    -0.06
    jun
    -0.06
    POSITIVE LOGITS
     almonds
    0.07
    ám
    0.07
     happen
    0.06
    .Many
    0.06
     conformity
    0.06
    _GROUP
    0.06
     reinforces
    0.06
     RESP
    0.06
    FillColor
    0.06
    ±
    0.06
    Act Density 0.020%

    No Known Activations