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

    Neuronpedia

    INDEX
    Explanations

    drawing or failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alebo
    0.42
     millas
    0.42
     utilizza
    0.40
     प्रणाम
    0.40
     প্রণাম
    0.40
     പരിശോധ
    0.39
     poprzez
    0.39
    verifica
    0.39
    ाग्राम
    0.39
     quelcon
    0.38
    POSITIVE LOGITS
     IMF
    0.41
     day
    0.40
     first
    0.36
     Hygien
    0.36
     MMO
    0.35
     Moment
    0.35
     Legends
    0.34
     FMC
    0.34
     b
    0.34
     Director
    0.34
    Act Density 0.000%

    No Known Activations