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

    Neuronpedia

    INDEX
    Explanations

    cling to, avoid, their standoff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Korean
    0.44
    解決
    0.41
    ylvan
    0.39
     publicity
    0.39
    Vegan
    0.39
    ジュニア
    0.38
     Korean
    0.38
    allyl
    0.38
    Weyl
    0.37
    UI
    0.37
    POSITIVE LOGITS
     Crunch
    0.43
     Rovio
    0.42
    걱
    0.42
     sesame
    0.41
    ộm
    0.40
     distanc
    0.40
     shroud
    0.40
    ioxide
    0.39
    Shroud
    0.39
     சிவப்பு
    0.38
    Act Density 0.000%

    No Known Activations