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

    Neuronpedia

    INDEX
    Explanations

    technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rituals
    -0.07
    _vi
    -0.07
     بیشتری
    -0.06
     republika
    -0.06
     captains
    -0.06
     vol
    -0.06
     strstr
    -0.06
     maximal
    -0.06
    划
    -0.06
    ές
    -0.06
    POSITIVE LOGITS
    oring
    0.07
    _ASSUME
    0.07
    gatsby
    0.07
    اهيم
    0.07
    FIELDS
    0.07
    _scale
    0.06
     против
    0.06
    pay
    0.06
    assessment
    0.06
    .look
    0.06
    Act Density 0.001%

    No Known Activations