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

    Neuronpedia

    INDEX
    Explanations

    crisis support resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paroles
    0.44
     remedial
    0.42
     woord
    0.42
     shabd
    0.42
     വാക്ക
    0.41
     beautifully
    0.40
     words
    0.40
     sayings
    0.39
     consacré
    0.39
     pokazuje
    0.38
    POSITIVE LOGITS
    ient
    0.39
    pseud
    0.38
    anut
    0.37
     Shipment
    0.37
    ido
    0.37
     Pseud
    0.37
    itic
    0.36
    ply
    0.36
     Import
    0.36
    Bin
    0.36
    Act Density 0.005%

    No Known Activations