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

    Neuronpedia

    INDEX
    Explanations

    bushes ahead, dangerous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    צות
    0.50
    Це
    0.46
    𝙞
    0.46
    점
    0.45
    чиго
    0.45
     умова
    0.44
    에서의
    0.44
    𝙖
    0.44
     WHAT
    0.43
    𝘽
    0.43
    POSITIVE LOGITS
    োধ
    0.49
     bathroom
    0.44
     fence
    0.42
     marked
    0.41
    marked
    0.41
     diar
    0.41
    ന്നെ
    0.40
     terima
    0.39
    empre
    0.39
     непро
    0.39
    Act Density 0.000%

    No Known Activations