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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     🙂
    -0.06
    Thumb
    -0.06
     금액
    -0.06
    送料無料
    -0.06
     Supplements
    -0.06
     Lexington
    -0.06
     pořad
    -0.06
     hugely
    -0.06
    -0.05
     hugged
    -0.05
    POSITIVE LOGITS
     комп
    0.07
    fl
    0.07
     özel
    0.07
     epic
    0.06
    522
    0.06
    ategori
    0.06
    _inst
    0.06
    .graph
    0.06
    _HINT
    0.06
    scatter
    0.06
    Act Density 0.000%

    No Known Activations