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

    Neuronpedia

    INDEX
    Explanations

    located

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hole
    -0.07
    还未
    -0.07
    类似
    -0.07
    дель
    -0.07
    具体
    -0.07
    php
    -0.06
     Poetry
    -0.06
    Uuid
    -0.06
    ContextHolder
    -0.06
    جمهورية
    -0.06
    POSITIVE LOGITS
     augmented
    0.07
    .Vertical
    0.07
    越來
    0.07
     […]↵↵
    0.07
    consult
    0.06
     /↵↵
    0.06
    зал
    0.06
    $route
    0.06
    ”.
    0.06
    によ
    0.06
    Act Density 0.037%

    No Known Activations