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

    Neuronpedia

    INDEX
    Explanations

    Sentence endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iami
    -0.06
    Level
    -0.06
    Allocator
    -0.06
    θεί
    -0.06
     díl
    -0.06
     �
    -0.06
    _Config
    -0.05
    Program
    -0.05
    [strlen
    -0.05
    otle
    -0.05
    POSITIVE LOGITS
     Tiger
    0.07
    .Since
    0.07
     Pearce
    0.06
    Earlier
    0.06
     glyph
    0.06
    TEE
    0.06
     rund
    0.06
    (frame
    0.06
    ?>↵↵
    0.06
     nich
    0.06
    Act Density 0.363%

    No Known Activations