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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.55
    tvguidetime
    -0.55
    Personendaten
    -0.54
    vyšší
    -0.54
    utilisons
    -0.52
     enkelte
    -0.51
     traseira
    -0.50
     originais
    -0.50
     zengin
    -0.49
    PrototypeOf
    -0.49
    POSITIVE LOGITS
     will
    0.59
     mean
    0.59
     Mean
    0.57
     verwijzen
    0.56
     have
    0.56
     can
    0.55
     Terms
    0.54
     terms
    0.54
     Lead
    0.54
     Books
    0.50
    Act Density 0.015%

    No Known Activations