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

    Neuronpedia

    INDEX
    Explanations

    HTML image type

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝔢
    -0.08
    ㅡ
    -0.08
    elines
    -0.07
    raft
    -0.07
     ware
    -0.07
    ᛫
    -0.07
     walkers
    -0.07
    aar
    -0.07
    Compatibility
    -0.07
     dra
    -0.07
    POSITIVE LOGITS
     Regression
    0.07
    LK
    0.07
     sponsor
    0.07
     Dudley
    0.07
     scares
    0.07
    Bay
    0.07
    ))).
    0.07
     slated
    0.07
    -heading
    0.07
     Discord
    0.07
    Act Density 0.000%

    No Known Activations