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

    Neuronpedia

    INDEX
    Explanations

    indemnification obligation clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ার
    0.56
    しまった
    0.54
    ा
    0.51
    kab
    0.51
    er
    0.50
     fibromyalgia
    0.50
    telefono
    0.49
     waters
    0.48
     jei
    0.47
     পদ্
    0.47
    POSITIVE LOGITS
    ia
    0.66
    ਾ
    0.65
    ic
    0.60
    wege
    0.55
    ከላከ
    0.55
    س
    0.54
     составляют
    0.54
    ोहित
    0.53
    शुभ
    0.53
     fpr
    0.53
    Act Density 0.001%

    No Known Activations