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

    Neuronpedia

    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deutschland
    -0.08
     premi
    -0.07
     microscopic
    -0.06
     ironically
    -0.06
     explanatory
    -0.06
    Loop
    -0.06
    _nh
    -0.06
     initials
    -0.06
     menší
    -0.06
     notation
    -0.06
    POSITIVE LOGITS
    took
    0.06
     गत
    0.06
     contenu
    0.06
     REFERENCES
    0.06
    href
    0.06
     bibliography
    0.06
    iliği
    0.06
     ontvang
    0.06
    iding
    0.06
    (stmt
    0.06
    Act Density 0.003%

    No Known Activations