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

    Neuronpedia

    INDEX
    Explanations

    LaTeX mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $\
    -0.71
    ↵↵
    -0.68
     of
    -0.55
     p
    -0.55
     is
    -0.53
     (
    -0.52
    .
    -0.52
    <eos>
    -0.51
     \
    -0.50
    -
    -0.50
    POSITIVE LOGITS
    ]")]
    1.09
     незавершена
    1.08
    TestingModule
    1.02
     CreateTagHelper
    1.01
     سكانية
    0.99
    twimg
    0.98
     ddelweddau
    0.97
    SBATCH
    0.97
    principalColumn
    0.97
     $_"
    0.94
    Act Density 1.723%

    No Known Activations