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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     слід
    -0.07
    :].
    -0.07
    iamo
    -0.07
    Printing
    -0.06
     }],↵
    -0.06
    .waitKey
    -0.06
    Ell
    -0.06
    .COLUMN
    -0.06
    thro
    -0.06
     probabil
    -0.06
    POSITIVE LOGITS
    isper
    0.07
     weighting
    0.06
    /components
    0.06
    ности
    0.06
     '\"
    0.06
     Rome
    0.06
     pequ
    0.06
    (resolve
    0.06
    -focus
    0.06
    (par
    0.06
    Act Density 0.003%

    No Known Activations