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

    Neuronpedia

    INDEX
    Explanations

    reactive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुलन
    -0.07
     Bu
    -0.07
     uzun
    -0.07
    Rub
    -0.06
     surprising
    -0.06
    圣
    -0.06
     Pan
    -0.06
    ику
    -0.06
    Stored
    -0.06
    .workflow
    -0.06
    POSITIVE LOGITS
     blatant
    0.08
     darf
    0.07
     și
    0.07
     hm
    0.07
     të
    0.06
     DEFIN
    0.06
    ์ก
    0.06
    [vi
    0.06
     DESCRIPTION
    0.06
    .readline
    0.06
    Act Density 0.014%

    No Known Activations