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

    Neuronpedia

    INDEX
    Explanations

    Days of the week

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Method
    -0.06
     Hollywood
    -0.06
     informed
    -0.06
     nostr
    -0.06
     decreasing
    -0.06
    construct
    -0.06
     Erotik
    -0.06
     definitive
    -0.06
     competitor
    -0.06
     пар
    -0.06
    POSITIVE LOGITS
    .setVisibility
    0.07
    iscing
    0.07
    τύ
    0.07
    aes
    0.06
    abb
    0.06
    EPS
    0.06
    KN
    0.06
    ABB
    0.06
    CAA
    0.06
    ]='
    0.06
    Act Density 0.083%

    No Known Activations