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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acious
    -0.07
     reinterpret
    -0.07
     escaping
    -0.07
    interpreted
    -0.07
     наз
    -0.07
     مطالعه
    -0.07
     harvesting
    -0.06
     daß
    -0.06
     چیست
    -0.06
     calibration
    -0.06
    POSITIVE LOGITS
    .stub
    0.06
    _DAC
    0.06
    .setBackground
    0.06
    _VERIFY
    0.06
    ичної
    0.06
    ':
    0.06
    �
    0.06
    SSI
    0.06
     hack
    0.06
    �i
    0.06
    Act Density 0.035%

    No Known Activations