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

    Neuronpedia

    INDEX
    Explanations

    locations or positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    隻
    -0.07
     drowned
    -0.07
     inadequate
    -0.07
    WHO
    -0.07
     travelers
    -0.07
    Rails
    -0.07
     THINK
    -0.06
    (IP
    -0.06
     doll
    -0.06
    _query
    -0.06
    POSITIVE LOGITS
    .linear
    0.08
     Job
    0.07
    _cid
    0.07
     Cloth
    0.07
    itions
    0.06
    -authored
    0.06
     enters
    0.06
    _type
    0.06
    ию
    0.06
    Leod
    0.06
    Act Density 0.021%

    No Known Activations