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

    Neuronpedia

    INDEX
    Explanations

    prefetching or caching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forb
    -0.08
     frustrations
    -0.07
     terc
    -0.07
     quatre
    -0.07
     folkl
    -0.07
     Frank
    -0.07
     Brah
    -0.07
     treaty
    -0.07
     Lemon
    -0.07
     вот
    -0.07
    POSITIVE LOGITS
     aggressively
    0.10
    hint
    0.09
    Acceler
    0.09
    Suggested
    0.09
    Hint
    0.09
     aggressive
    0.09
    Hints
    0.09
    抓
    0.09
    (foo
    0.09
     antecip
    0.09
    Act Density 0.002%

    No Known Activations