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

    Neuronpedia

    INDEX
    Explanations

    css color properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.36
    /
    0.33
    an
    0.32
    out
    0.32
    ed
    0.32
    ó
    0.32
    version
    0.31
    -
    0.30
    :
    0.30
    '
    0.30
    POSITIVE LOGITS
     justo
    0.38
     secretario
    0.37
     saluto
    0.37
     secretaria
    0.36
     viktigt
    0.34
     waren
    0.34
     estava
    0.34
     شاید
    0.34
     valamint
    0.34
     discapacidad
    0.33
    Act Density 0.007%

    No Known Activations