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

    Neuronpedia

    INDEX
    Explanations

    arising from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ד
    1.70
    ဠ
    1.57
     Recall
    1.55
    ことにより
    1.55
    ivative
    1.53
    ividual
    1.53
    こと
    1.51
    nn
    1.51
    eritud
    1.50
    1.49
    POSITIVE LOGITS
     fuss
    1.69
     personnes
    1.69
     volcan
    1.68
    На
    1.65
     jeux
    1.64
    Ка
    1.62
     diz
    1.60
     médiane
    1.58
     nur
    1.57
     heures
    1.56
    Act Density 0.000%

    No Known Activations