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

    Neuronpedia

    INDEX
    Explanations

    Newton

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ازد
    -0.06
    compat
    -0.06
    .Override
    -0.06
     Hispanic
    -0.06
     oauth
    -0.06
     hjem
    -0.06
    $select
    -0.06
    Ctrls
    -0.06
    lineno
    -0.06
     GIVEN
    -0.06
    POSITIVE LOGITS
    اية
    0.06
    ("\\
    0.06
     Extremely
    0.06
    ifter
    0.06
    836
    0.06
     mutation
    0.06
     transformative
    0.06
    與
    0.06
     unsigned
    0.06
    ?),
    0.06
    Act Density 0.000%

    No Known Activations