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

    Neuronpedia

    INDEX
    Explanations

    category separators, especially ampersands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そのような
    0.39
     Kisan
    0.38
     indications
    0.38
     осіб
    0.37
    শাখ
    0.37
     erg
    0.37
     ergeben
    0.37
     уены
    0.37
     そんな
    0.36
     adjudication
    0.36
    POSITIVE LOGITS
     &
    0.77
    ＆
    0.61
    &
    0.59
     &(
    0.58
     &'
    0.55
     \&
    0.53
    &$
    0.53
     (&
    0.52
     &\
    0.52
     &$
    0.51
    Act Density 0.004%

    No Known Activations