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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DataType
    -0.07
    _break
    -0.07
    (ir
    -0.07
    _SPLIT
    -0.06
    IRROR
    -0.06
    umped
    -0.06
    691
    -0.06
    znam
    -0.06
    .keep
    -0.06
    udoku
    -0.06
    POSITIVE LOGITS
     Teachers
    0.07
     P
    0.07
    '){
    0.07
     teachers
    0.07
     mapped
    0.07
    ')
    0.06
     byly
    0.06
     eager
    0.06
     Iz
    0.06
     Д
    0.06
    Act Density 0.070%

    No Known Activations