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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     süreci
    -0.08
     subsidi
    -0.07
    627
    -0.07
     në
    -0.06
    Prefix
    -0.06
    .tx
    -0.06
     лица
    -0.06
    (Book
    -0.06
     Houses
    -0.06
    -task
    -0.06
    POSITIVE LOGITS
    _imm
    0.06
    rewrite
    0.06
     Piano
    0.06
    opian
    0.06
     adapt
    0.06
     fans
    0.06
    egral
    0.06
    ATFORM
    0.06
    یز
    0.06
    _parsed
    0.06
    Act Density 0.026%

    No Known Activations