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

    Neuronpedia

    INDEX
    Explanations

    ikop sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tarot
    0.92
     Pokémon
    0.88
     WooCommerce
    0.87
     Kubernetes
    0.84
     affirmations
    0.83
     Nietzsche
    0.82
     incompatible
    0.81
     exposition
    0.81
     Semantic
    0.81
     existential
    0.81
    POSITIVE LOGITS
    bc
    1.27
    bd
    1.27
    cp
    1.26
    bx
    1.24
    bf
    1.24
    dc
    1.23
    dp
    1.23
    bp
    1.22
    rb
    1.21
    bm
    1.19
    Act Density 0.748%

    No Known Activations