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

    Neuronpedia

    INDEX
    Explanations

    submenu under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    J
    0.47
    S
    0.46
    N
    0.46
    L
    0.45
     volut
    0.44
    Q
    0.44
     samostat
    0.44
    Jan
    0.43
     Jann
    0.43
    AZ
    0.42
    POSITIVE LOGITS
    ∈</
    0.50
     crossbow
    0.49
    旂
    0.48
     נ
    0.46
    🥢
    0.45
     Reactors
    0.44
     गीत
    0.44
     show
    0.44
     ಸ್ಪ
    0.44
     Syracuse
    0.43
    Act Density 0.006%

    No Known Activations