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

    Neuronpedia

    INDEX
    Explanations

    9 exits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    想法
    0.40
     Cliente
    0.40
    Hed
    0.40
    Hoch
    0.39
     Держа
    0.39
    Ờ
    0.39
    ✽
    0.39
    Flat
    0.39
    inių
    0.38
    깍
    0.38
    POSITIVE LOGITS
    fhir
    0.39
     Errors
    0.37
    पर्यंत
    0.37
     Ronaldo
    0.36
    더라도
    0.35
    ъз
    0.35
     errors
    0.34
     ond
    0.34
    emorrh
    0.34
     morate
    0.34
    Act Density 0.000%

    No Known Activations