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
    Minus
    -0.07
    })",
    -0.06
     LS
    -0.06
    Fac
    -0.06
    ania
    -0.06
     overflowing
    -0.06
    urst
    -0.06
    Hour
    -0.06
    ]))
    -0.06
     love
    -0.06
    POSITIVE LOGITS
    (term
    0.06
    ,(
    0.06
    toThrow
    0.06
     Wes
    0.06
    rootScope
    0.06
     блок
    0.06
    .gl
    0.06
     plá
    0.06
    fails
    0.06
     &);↵
    0.06
    Act Density 0.041%

    No Known Activations