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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "#
    -0.09
     agua
    -0.08
     resort
    -0.07
    _ABC
    -0.07
    "></
    -0.07
     REFER
    -0.07
     viv
    -0.07
     zeigt
    -0.06
     recurs
    -0.06
     rod
    -0.06
    POSITIVE LOGITS
    decoder
    0.07
    _logic
    0.07
    蹐
    0.06
    짴
    0.06
     specialize
    0.06
    颀
    0.06
    andatory
    0.06
    خص
    0.06
    umbnails
    0.06
    BE
    0.06
    Act Density 0.043%

    No Known Activations