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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Psr
    -0.07
    (std
    -0.07
     Sher
    -0.07
     side
    -0.06
     Shortly
    -0.06
     Unauthorized
    -0.06
    .");
↵
    -0.06
    STER
    -0.06
     completely
    -0.06
    ysterious
    -0.06
    POSITIVE LOGITS
     malaysia
    0.07
    的情感
    0.07
    $status
    0.07
    policy
    0.07
     semen
    0.07
    邵
    0.07
    issy
    0.07
    ⓛ
    0.06
     frameworks
    0.06
    _enable
    0.06
    Act Density 0.025%

    No Known Activations