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

    Neuronpedia

    INDEX
    Explanations

    someone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Но
    -0.07
    ournal
    -0.06
    ера
    -0.06
     nối
    -0.06
    ede
    -0.06
     NCAA
    -0.06
    IPLE
    -0.06
    onom
    -0.06
    assi
    -0.06
    OURNAL
    -0.06
    POSITIVE LOGITS
    rug
    0.07
    warnings
    0.07
     무엇
    0.07
     uyg
    0.07
    -rating
    0.07
     перел
    0.06
     tumble
    0.06
     авг
    0.06
     decision
    0.06
     statements
    0.06
    Act Density 0.000%

    No Known Activations