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

    Neuronpedia

    INDEX
    Explanations

    counting sort reconstruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     милли
    0.38
    ultra
    0.38
    zad
    0.37
     McGrath
    0.37
    PTI
    0.36
    Liability
    0.36
    chemistry
    0.36
    Baik
    0.36
    datetime
    0.35
    ότητα
    0.35
    POSITIVE LOGITS
     reconstruct
    0.44
     OUTPUT
    0.43
     Stable
    0.41
    જબ
    0.41
     rearr
    0.41
     stable
    0.40
     Codes
    0.39
     reconstructing
    0.39
     RAD
    0.38
     output
    0.38
    Act Density 0.004%

    No Known Activations