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

    Neuronpedia

    INDEX
    Explanations

    animals, animal facts, and jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calibrations
    0.39
     stabil
    0.39
     calibr
    0.38
     tributes
    0.38
     derivations
    0.38
     prosecutions
    0.38
     couplings
    0.37
     payloads
    0.37
     hashlib
    0.36
    aissez
    0.36
    POSITIVE LOGITS
     hayvan
    0.42
     animali
    0.38
     animale
    0.37
    画像
    0.37
    簡易
    0.37
     Tiere
    0.37
    ática
    0.37
    ência
    0.36
     giovani
    0.35
     yeni
    0.35
    Act Density 0.001%

    No Known Activations