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

    Neuronpedia

    INDEX
    Explanations

    mobile phone/apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ע
    0.72
    各式
    0.68
    ClrBit
    0.68
    湿
    0.66
    ل
    0.66
    effect
    0.62
     dry
    0.62
     건
    0.61
     limb
    0.61
    水
    0.61
    POSITIVE LOGITS
     existir
    0.92
     отдельные
    0.89
     темы
    0.88
     Lehrer
    0.87
     semanas
    0.86
     humanas
    0.85
     Argonne
    0.84
    மாண
    0.83
     claras
    0.83
     Если
    0.82
    Act Density 0.004%

    No Known Activations