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

    Neuronpedia

    INDEX
    Explanations

    contexts and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ใน
    0.59
     în
    0.50
     در
    0.49
    可在
    0.47
     στο
    0.46
    年在
    0.46
    ในการ
    0.46
     στις
    0.46
     into
    0.46
     в
    0.46
    POSITIVE LOGITS
     guise
    0.73
    的情况下
    0.71
     وفي
    0.68
     contexts
    0.66
    看来
    0.66
    的基础上
    0.63
     midst
    0.63
     contexto
    0.61
    ၌
    0.60
     contextos
    0.60
    Act Density 0.296%

    No Known Activations