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

    Neuronpedia

    INDEX
    Explanations

    French Touch, porcelain doll

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contribution
    0.39
    lake
    0.37
     Інтэр
    0.36
    ड्रा
    0.36
     ይታ
    0.36
    recon
    0.35
     larc
    0.35
    abet
    0.35
     हाउ
    0.35
     Lori
    0.35
    POSITIVE LOGITS
    便
    0.41
    служ
    0.41
     speechSynthesis
    0.40
    诫
    0.39
    辩
    0.38
    闱
    0.38
    కర
    0.37
     unglaublich
    0.37
    省级
    0.36
     Schlaf
    0.36
    Act Density 0.002%

    No Known Activations