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

    Neuronpedia

    INDEX
    Explanations

    various ratings or scores associated with opinions or reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    definitions and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كومونز
    -0.78
     surla
    -0.77
     ſind
    -0.75
    contentLoaded
    -0.71
    IntoConstraints
    -0.71
    <unused41>
    -0.69
    <unused52>
    -0.69
    <unused8>
    -0.69
    <unused74>
    -0.69
    <unused14>
    -0.69
    POSITIVE LOGITS
     nabíz
    0.39
     posled
    0.39
     medios
    0.38
     asmen
    0.38
     prostřed
    0.38
     estándares
    0.36
     cobrar
    0.36
     Verhandlungen
    0.36
     formatos
    0.36
     Sünde
    0.35
    Act Density 0.093%

    No Known Activations