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

    Neuronpedia

    INDEX
    Explanations

    service numbers and hotlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ล่ะ
    0.71
    sembl
    0.67
    يميديا
    0.63
    qld
    0.59
    ifikation
    0.58
    oderma
    0.58
     bzw
    0.57
     troubles
    0.57
     ModelAndView
    0.56
     passagem
    0.56
    POSITIVE LOGITS
    ×
    1.06
     ×
    0.86
    x
    0.81
     Nar
    0.80
    ็
    0.80
    ˟
    0.78
     Seven
    0.77
     Carlyle
    0.77
     সাত
    0.76
     seven
    0.75
    Act Density 0.019%

    No Known Activations