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

    Neuronpedia

    INDEX
    Explanations

    viability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relevant
    -0.99
     applicable
    -0.97
    SequentialGroup
    -0.93
     appropriate
    -0.90
    relevant
    -0.90
     relevantes
    -0.88
     relevante
    -0.86
     ModelExpression
    -0.84
    ConstraintMaker
    -0.80
    TagMode
    -0.79
    POSITIVE LOGITS
     of
    0.56
     to
    0.52
     mar
    0.46
     ham
    0.45
    ้ว
    0.44
    ly
    0.43
    ,
    0.43
    immobili
    0.43
    ised
    0.42
     landing
    0.42
    Act Density 0.096%

    No Known Activations