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

    Neuronpedia

    INDEX
    Explanations

    continues|discontinues|disappears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    傾向
    0.44
     면
    0.39
     مص
    0.37
    ဝ
    0.36
    <0xA6>
    0.36
    acylglycer
    0.35
    Hom
    0.35
     loosen
    0.35
     neod
    0.35
     Akar
    0.35
    POSITIVE LOGITS
     discontinued
    0.40
    λέον
    0.40
     continues
    0.40
    ijdens
    0.39
     discontinue
    0.38
    mazing
    0.38
     disappears
    0.38
    urable
    0.38
     vardır
    0.37
     भारतातील
    0.37
    Act Density 0.000%

    No Known Activations