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

    Neuronpedia

    INDEX
    Explanations

    links/identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    יס
    -0.08
     Cummings
    -0.07
    _counts
    -0.07
    婫
    -0.07
    -free
    -0.07
    /S
    -0.07
    بد
    -0.07
     substitutions
    -0.06
     y
    -0.06
     próprio
    -0.06
    POSITIVE LOGITS
     Latter
    0.07
     abc
    0.07
     Dublin
    0.07
    .TRAILING
    0.07
    憧
    0.06
    -disabled
    0.06
    �
    0.06
    菱
    0.06
     Tobias
    0.06
    LTRB
    0.06
    Act Density 0.001%

    No Known Activations