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

    Neuronpedia

    INDEX
    Explanations

    investigate too closely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yuan
    0.44
     KMnO
    0.42
    ကောင်း
    0.41
    консу
    0.41
     አማ
    0.39
     isso
    0.39
     yalnız
    0.38
    Transportation
    0.37
    лябин
    0.37
     permangan
    0.37
    POSITIVE LOGITS
     Becker
    0.44
    రీ
    0.40
     reactive
    0.38
     Reactive
    0.38
     breeder
    0.38
    맥
    0.37
     Auf
    0.36
    elius
    0.35
    धित
    0.35
    æld
    0.35
    Act Density 0.000%

    No Known Activations