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

    Neuronpedia

    INDEX
    Explanations

    formal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    petition
    -0.08
    -striped
    -0.07
     insistence
    -0.07
    둠
    -0.07
    .scalar
    -0.07
    unnable
    -0.07
     right
    -0.07
    畏
    -0.07
    送给
    -0.07
    𐌿
    -0.07
    POSITIVE LOGITS
    _SPE
    0.07
    .fits
    0.07
     można
    0.07
     ble
    0.06
     Malay
    0.06
     favourable
    0.06
    .startswith
    0.06
     statt
    0.06
    _PROFILE
    0.06
    .syn
    0.06
    Act Density 0.061%

    No Known Activations