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

    Neuronpedia

    INDEX
    Explanations

    WITHOUT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     motivating
    -0.07
    _RETRY
    -0.07
    _mob
    -0.07
    ݬ
    -0.07
    _send
    -0.07
    .pad
    -0.07
     Mediterranean
    -0.07
     Lead
    -0.07
    _BLK
    -0.06
    툩
    -0.06
    POSITIVE LOGITS
     Diese
    0.07
    אוניב
    0.07
     succes
    0.07
     Unity
    0.07
    ег
    0.07
     rects
    0.07
    _In
    0.06
    #else
    0.06
     cette
    0.06
    typings
    0.06
    Act Density 0.001%

    No Known Activations