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

    Neuronpedia

    INDEX
    Explanations

    General text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    col
    -0.08
    opers
    -0.07
    ssi
    -0.07
    ash
    -0.06
    $where
    -0.06
    agent
    -0.06
     쪽지
    -0.06
     sow
    -0.06
     Sala
    -0.06
     cities
    -0.06
    POSITIVE LOGITS
     shredded
    0.06
     granite
    0.06
    []↵
    0.06
     scientifically
    0.06
    .plist
    0.06
     gaps
    0.06
    .SelectedIndex
    0.06
    Assignable
    0.06
    .alloc
    0.06
     Möglichkeit
    0.06
    Act Density 0.006%

    No Known Activations