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

    Neuronpedia

    INDEX
    Explanations

    remove all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    入住
    0.47
    wantErr
    0.41
    ೋನ್
    0.40
    timeout
    0.40
    Todd
    0.40
     vrijeme
    0.39
     perks
    0.38
    email
    0.38
     notícias
    0.38
    scrollTo
    0.37
    POSITIVE LOGITS
     Kinetic
    0.46
     सशस्त्र
    0.44
     USSR
    0.44
    線性
    0.44
     Chap
    0.43
     kinetic
    0.43
     CHAP
    0.43
     Figur
    0.42
     Hamiltonian
    0.42
     Schrödinger
    0.42
    Act Density 0.002%

    No Known Activations