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

    Neuronpedia

    INDEX
    Explanations

    merge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _nl
    -0.07
     dictionaries
    -0.07
     heyec
    -0.07
     Cathedral
    -0.06
     qs
    -0.06
    ضوع
    -0.06
     سر
    -0.06
    attrs
    -0.06
    ATCH
    -0.06
     STRICT
    -0.06
    POSITIVE LOGITS
     é
    0.07
     Jama
    0.07
    +'_
    0.07
    简
    0.07
     پژوهش
    0.06
    venth
    0.06
     wholes
    0.06
     reconstruct
    0.06
     geral
    0.06
    详情
    0.06
    Act Density 0.004%

    No Known Activations