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

    Neuronpedia

    INDEX
    Explanations

    Deno, JSON, WASM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Severe
    0.40
    Elemental
    0.39
    Drug
    0.38
     Severe
    0.37
    ElementType
    0.36
    ওয়ার
    0.34
     uintptr
    0.34
    TextAppearance
    0.34
    Liqu
    0.34
    rH
    0.33
    POSITIVE LOGITS
    menos
    0.37
     mengerjakan
    0.37
    cool
    0.36
    mic
    0.35
    ডেন
    0.35
     mic
    0.35
    aturan
    0.35
    ฏ
    0.35
    beans
    0.34
     અંત
    0.34
    Act Density 0.002%

    No Known Activations