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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating obligation or necessity

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

    modal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.81
    OGND
    -0.81
    Personendaten
    -0.77
     saveiro
    -0.69
     desmotivaciones
    -0.69
     estekak
    -0.68
    pecabe
    -0.68
    GEBURTSDATUM
    -0.65
     čierna
    -0.65
    adaptiveStyles
    -0.65
    POSITIVE LOGITS
     also
    0.68
     be
    0.63
     not
    0.57
     have
    0.56
     
    0.54
    0.53
    is
    0.53
    tig
    0.51
    and
    0.50
    I
    0.50
    Act Density 0.054%
    No Known Activations