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

    Neuronpedia

    INDEX
    Explanations

    saccharide endings and compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     certo
    1.85
    ёнок
    1.76
     Ă
    1.73
     cóm
    1.65
    此之外
    1.64
    outs
    1.64
     brake
    1.63
     Scream
    1.61
     responsável
    1.59
    𝗔
    1.58
    POSITIVE LOGITS
    tedir
    1.60
    er
    1.59
    mael
    1.49
    ার
    1.47
     thức
    1.47
    localObject
    1.42
    ोत्तर
    1.35
    💭
    1.34
     illuminating
    1.33
    γε
    1.32
    Act Density 0.015%

    No Known Activations