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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ers
    -0.07
     todo
    -0.07
     come
    -0.07
    .recipe
    -0.07
     retries
    -0.06
     woods
    -0.06
     warn
    -0.06
    宫
    -0.06
     perceive
    -0.06
     free
    -0.06
    POSITIVE LOGITS
     Craig
    0.07
    ософ
    0.06
     hộp
    0.06
    Crear
    0.06
    ันต
    0.06
    theValue
    0.06
    дать
    0.06
    }.
    0.06
    }↵↵↵
    0.06
    ظهر
    0.06
    Act Density 0.020%

    No Known Activations