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

    Neuronpedia

    INDEX
    Explanations

    introducing explanations or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.41
     moieties
    0.40
     fellowships
    0.34
     correlations
    0.34
     condos
    0.33
    ي
    0.33
    lari
    0.33
    erende
    0.33
    ੇ
    0.33
     dilemmas
    0.32
    POSITIVE LOGITS
    ud
    0.49
    с
    0.46
    o
    0.43
    ono
    0.40
    кий
    0.39
    oc
    0.38
    <0xA5>
    0.38
    1
    0.38
    которы
    0.37
     políticos
    0.37
    Act Density 0.575%

    No Known Activations