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

    Neuronpedia

    INDEX
    Explanations

    the word 'calculated' and potentially other words meaning 'change' or 'convert'

    oai_token-act-pair · gemini-2.0-flash

    calculated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enfans
    -1.11
    ^(@)
    -1.05
     chré
    -1.01
     vectorielles
    -0.94
    MERCIAL
    -0.94
     vettoriale
    -0.93
    paravant
    -0.91
     nationaux
    -0.91
     quæ
    -0.90
     pauv
    -0.89
    POSITIVE LOGITS
    \{\\
    0.82
    IntoConstraints
    0.65
    ArgsConstructor
    0.65
    à
    0.60
    ParallelGroup
    0.60
    ia
    0.59
     festi
    0.59
    ta
    0.59
     فريبيس
    0.59
    qu
    0.58
    Act Density 1.918%

    No Known Activations