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

    Neuronpedia

    INDEX
    Explanations

    slight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faint
    -1.00
     feeble
    -0.97
     debole
    -0.95
     weakly
    -0.93
     subtle
    -0.92
     weak
    -0.91
    subtle
    -0.91
     débil
    -0.88
     Weak
    -0.85
     Subtle
    -0.84
    POSITIVE LOGITS
    ly
    0.80
     EClass
    0.64
     unknownFields
    0.64
    SharedCtor
    0.57
    ness
    0.50
    nesses
    0.50
    Pranala
    0.49
    جغرافيا
    0.49
    ValueStyle
    0.48
     enough
    0.48
    Act Density 0.036%

    No Known Activations