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

    Neuronpedia

    INDEX
    Explanations

    when used to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     posib
    -1.59
    rogens
    -1.57
    曁
    -1.52
     robusto
    -1.50
     residente
    -1.50
     contenta
    -1.50
     belga
    -1.49
     lini
    -1.49
     minimalista
    -1.47
     kelebihan
    -1.46
    POSITIVE LOGITS
    There
    1.80
    When
    1.75
    The
    1.67
    1
    1.66
    Some
    1.59
    Many
    1.58
     While
    1.55
    You
    1.55
     and
    1.54
     These
    1.50
    Act Density 0.046%

    No Known Activations