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

    Neuronpedia

    INDEX
    Explanations

    bit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.75
     saites
    -0.70
    expandindo
    -0.68
    BagConstraints
    -0.67
    -0.66
    LookAnd
    -0.65
     disambiguazione
    -0.65
    andExpect
    -0.64
    Personensuche
    -0.63
    >--}}
    -0.62
    POSITIVE LOGITS
    icana
    0.50
     Dr
    0.50
    agen
    0.43
    ↵↵
    0.43
    akan
    0.43
     space
    0.42
     average
    0.42
     infar
    0.42
    Dr
    0.41
    ofas
    0.41
    Act Density 0.013%

    No Known Activations