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

    Neuronpedia

    INDEX
    Explanations

    pop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estimés
    -0.55
     ostavi
    -0.55
    AndEndTag
    -0.54
    SourceChecksum
    -0.54
     Италијани
    -0.52
    RRect
    -0.52
    IBar
    -0.51
    iral
    -0.50
     Zol
    -0.50
     विश्वसनीयता
    -0.50
    POSITIVE LOGITS
    poor
    0.49
    embang
    0.48
    Mozilla
    0.46
    WriteBarrier
    0.46
    󠁿
    0.46
     poor
    0.46
    ounid
    0.45
    MCH
    0.44
     cérami
    0.44
    etcode
    0.44
    Act Density 0.000%

    No Known Activations