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

    Neuronpedia

    INDEX
    Explanations

    @json@ or statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atho
    0.53
    Date
    0.43
    AST
    0.43
    LLY
    0.41
    ância
    0.40
    Launch
    0.40
    Datas
    0.40
     estómago
    0.40
    Scape
    0.39
    Range
    0.39
    POSITIVE LOGITS
     termasuk
    0.38
    环保
    0.38
     proclaims
    0.38
     ensures
    0.38
    proclaimed
    0.38
     Singing
    0.37
     Ensuring
    0.37
    ර
    0.37
     Warming
    0.36
     Shout
    0.36
    Act Density 0.000%

    No Known Activations