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

    Neuronpedia

    INDEX
    Explanations

    instruction, evidence, demonstrate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lüğ
    0.50
    zinho
    0.48
     навы
    0.48
    𝐨
    0.48
     mezi
    0.47
    ة
    0.47
    ز
    0.46
    л
    0.46
    <0x9D>
    0.46
     bästa
    0.45
    POSITIVE LOGITS
    prima
    0.56
     cranberries
    0.53
     charges
    0.50
    a
    0.49
     on
    0.49
    week
    0.48
    コロナ
    0.48
     antivirus
    0.47
     Closer
    0.47
    Crown
    0.47
    Act Density 0.000%

    No Known Activations