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

    Neuronpedia

    INDEX
    Explanations

    steer clear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.93
    l
    0.91
    a
    0.87
    </h3>
    0.82
    ان
    0.81
    </sub>
    0.77
    an
    0.77
    ط
    0.76
    tion
    0.75
    া
    0.74
    POSITIVE LOGITS
    az
    0.89
     vendeurs
    0.84
    slotBox
    0.80
    ない
    0.79
     steer
    0.79
     вещества
    0.78
     avoid
    0.77
    od
    0.76
     consejos
    0.76
    ்கள்
    0.75
    Act Density 0.001%

    No Known Activations