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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     функци
    -0.07
    _Entity
    -0.07
    529
    -0.07
    _REFERENCE
    -0.06
    Detector
    -0.06
    -tree
    -0.06
     Росії
    -0.06
    &&
    -0.06
    (strtolower
    -0.06
    text
    -0.06
    POSITIVE LOGITS
     /↵
    0.07
    PY
    0.07
    iglia
    0.06
     istediğiniz
    0.06
    aside
    0.06
    ]
↵
    0.06
    .act
    0.06
    ==========
    0.06
    IMUM
    0.06
     PCM
    0.06
    Act Density 0.185%

    No Known Activations