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

    Neuronpedia

    INDEX
    Explanations

    questions, how-much, what-if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    1.81
    ри
    1.79
    কে
    1.73
    ate
    1.67
    tion
    1.67
    ात
    1.63
    ían
    1.60
    .
    1.58
    id
    1.54
    רו
    1.54
    POSITIVE LOGITS
    𝑵
    1.77
    じて
    1.71
    ين
    1.61
    SequentialGroup
    1.57
     officiel
    1.57
     ovales
    1.55
    咶
    1.55
     internationaux
    1.45
    حة
    1.44
    شهاد
    1.43
    Act Density 0.001%

    No Known Activations