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

    Neuronpedia

    INDEX
    Explanations

    citations and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     becauſe
    -0.69
     raiſ
    -0.66
     againſt
    -0.60
     ſay
    -0.60
     chofe
    -0.59
    complexContent
    -0.59
    WireFormatLite
    -0.59
     uſed
    -0.58
     neceffary
    -0.58
    SequentialGroup
    -0.58
    POSITIVE LOGITS
     OFDb
    0.60
    expandindo
    0.59
     véritables
    0.52
    providedIn
    0.52
     vrais
    0.50
    thâu
    0.48
    breos
    0.48
     vecka
    0.47
     pertes
    0.46
     claridad
    0.45
    Act Density 0.001%

    No Known Activations