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

    Neuronpedia

    INDEX
    Explanations

    tutor, conscience, recommendation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Raza
    0.52
    0.50
     темы
    0.49
     temi
    0.49
     Cez
    0.48
     laborers
    0.48
    𝓜
    0.46
     stric
    0.44
     appease
    0.44
    𓇼
    0.43
    POSITIVE LOGITS
    of
    0.50
     文件
    0.49
    $,
    0.46
    ]，
    0.44
     金
    0.43
    "，
    0.42
     voort
    0.42
    ”，
    0.40
    䡉
    0.40
     分
    0.40
    Act Density 0.004%

    No Known Activations