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

    Neuronpedia

    INDEX
    Explanations

    requirements or offers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interrogation
    -0.07
     Sonia
    -0.07
    Δ
    -0.07
    𝐙
    -0.07
    SVG
    -0.07
    ritt
    -0.07
     videog
    -0.07
     cancellationToken
    -0.07
    Insets
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    永
    0.08
    _DER
    0.07
    .custom
    0.07
    ظم
    0.07
     unilateral
    0.07
    wins
    0.07
    成都
    0.06
     wash
    0.06
    树
    0.06
     join
    0.06
    Act Density 0.089%

    No Known Activations