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

    Neuronpedia

    INDEX
    Explanations

    diverse recall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.55
    าย
    0.44
     Diane
    0.44
    าก
    0.43
     analytical
    0.43
     ignorance
    0.43
    کیل
    0.42
     FOM
    0.41
     knobs
    0.41
    かせ
    0.41
    POSITIVE LOGITS
    ఎస్
    0.48
    ఆర్
    0.46
     സ്
    0.46
     phoenix
    0.45
     amerikan
    0.44
     britann
    0.44
    Multicolored
    0.43
    屋外
    0.42
     Vorteile
    0.41
     hochwertige
    0.41
    Act Density 0.005%

    No Known Activations