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

    Neuronpedia

    INDEX
    Explanations

    state and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    -0.84
     näin
    -0.79
    stantial
    -0.78
    jaguar
    -0.78
    pgfplots
    -0.77
    ,!
    -0.77
     for
    -0.76
    Epidemiology
    -0.76
     or
    -0.75
     supposedly
    -0.75
    POSITIVE LOGITS
     servicio
    0.99
    そこは
    0.95
    調味料
    0.93
     COU
    0.91
     cay
    0.91
    unii
    0.90
    心灵
    0.90
     Oost
    0.89
     下着
    0.88
     mág
    0.88
    Act Density 0.000%

    No Known Activations