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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pull
    -0.07
     plaint
    -0.07
    ̧
    -0.07
     batt
    -0.07
    gew
    -0.06
    媒体
    -0.06
     Peter
    -0.06
     filt
    -0.06
    .Mutable
    -0.06
    φερ
    -0.06
    POSITIVE LOGITS
    _similarity
    0.07
     순간
    0.07
    _SPACE
    0.06
    $output
    0.06
    více
    0.06
     :=↵
    0.06
    _seed
    0.06
    ↵
    0.06
    *a
    0.06
     Mississippi
    0.06
    Act Density 0.002%

    No Known Activations