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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phái
    -0.07
    .SQLite
    -0.07
    general
    -0.06
    Alias
    -0.06
    mnt
    -0.06
    (stmt
    -0.06
    NUM
    -0.06
     листоп
    -0.06
    eum
    -0.06
    monitor
    -0.06
    POSITIVE LOGITS
     stitched
    0.07
    beth
    0.07
     strokes
    0.06
     excitement
    0.06
    .damage
    0.06
    _CAN
    0.06
    ề
    0.06
    }))↵↵
    0.06
     trump
    0.06
     gun
    0.06
    Act Density 0.043%

    No Known Activations