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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -parse
    -0.07
     몽
    -0.07
     collapsing
    -0.06
     mí
    -0.06
     اختیار
    -0.06
    -terrorism
    -0.06
    ندر
    -0.06
     внес
    -0.06
     ideals
    -0.06
    queries
    -0.06
    POSITIVE LOGITS
    )$
    0.07
    ).</
    0.07
     Trip
    0.06
    ــــــــ
    0.06
    jpg
    0.06
    .stdout
    0.06
     Engagement
    0.06
     peter
    0.06
    prefs
    0.06
    eacher
    0.06
    Act Density 0.007%

    No Known Activations