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

    Neuronpedia

    INDEX
    Explanations

    transaction, attack, limitations, POA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hues
    0.75
     trust
    0.75
     defending
    0.74
    រី
    0.73
     bumps
    0.73
     irrigation
    0.71
     coils
    0.70
     flares
    0.70
    ана
    0.69
     compounds
    0.69
    POSITIVE LOGITS
    ం
    0.89
    ü
    0.87
    ை
    0.86
    is
    0.79
    ى
    0.78
     conversar
    0.78
    ين
    0.77
    цию
    0.74
     caminho
    0.74
     Таким
    0.73
    Act Density 0.002%

    No Known Activations