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

    Neuronpedia

    INDEX
    Explanations

    SS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fleets
    -0.07
     enfermed
    -0.07
    铻
    -0.06
     düny
    -0.06
    .DataBindings
    -0.06
     הממשלה
    -0.06
     colle
    -0.06
     antibiotic
    -0.06
    �
    -0.06
     Punk
    -0.06
    POSITIVE LOGITS
    headers
    0.07
    qq
    0.07
    adb
    0.07
     erase
    0.07
    蝴蝶
    0.07
     DV
    0.07
    Currency
    0.07
     sequential
    0.07
    ᴀ
    0.07
    (Json
    0.07
    Act Density 0.006%

    No Known Activations