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

    Neuronpedia

    INDEX
    Explanations

    H words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.40
    otiti
    0.39
    hydrocèle
    0.38
    ಕೊ
    0.38
    urètre
    0.38
    isatie
    0.37
    ificação
    0.37
    سه
    0.37
    Appending
    0.35
    omey
    0.35
    POSITIVE LOGITS
     H
    0.58
     HO
    0.52
     HS
    0.51
     HL
    0.49
     HP
    0.47
     HCC
    0.46
     HC
    0.46
     HSP
    0.46
     HM
    0.45
     HB
    0.45
    Act Density 0.097%

    No Known Activations