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

    Neuronpedia

    INDEX
    Explanations

    implies or means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sebagian
    0.75
     olika
    0.74
     assez
    0.73
     abbastanza
    0.72
     unlike
    0.71
    unlike
    0.69
     einiger
    0.69
     особы
    0.67
     bastante
    0.66
     devait
    0.66
    POSITIVE LOGITS
     =
    1.24
    ＝
    1.16
    =(
    1.15
    =
    1.11
     correspondingly
    1.09
    >=</
    1.05
    也就
    1.04
     &=
    1.03
    意味着
    1.02
     $=$
    1.01
    Act Density 0.472%

    No Known Activations