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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yš
    -0.07
    ephy
    -0.07
    ulated
    -0.07
    ']*
    -0.07
    getColumn
    -0.07
    -outs
    -0.06
    adic
    -0.06
    ilmektedir
    -0.06
    geben
    -0.06
    ],
    -0.06
    POSITIVE LOGITS
    _additional
    0.07
     토
    0.07
     useStyles
    0.07
    =logging
    0.06
    chter
    0.06
    (&:
    0.06
     앨
    0.06
     Кост
    0.06
    [class
    0.06
     grant
    0.06
    Act Density 0.001%

    No Known Activations