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

    Neuronpedia

    INDEX
    Explanations

    crafting captivating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Massage
    0.37
     triad
    0.35
     камен
    0.35
     turns
    0.34
    εδ
    0.34
    нед
    0.33
    uitary
    0.33
    Large
    0.32
    Alternate
    0.31
     Tri
    0.31
    POSITIVE LOGITS
     关闭
    0.43
    雩
    0.42
     गर्ल
    0.41
    cov
    0.41
    jsko
    0.41
     брен
    0.41
    セール
    0.40
     தொடர்பாக
    0.40
     klien
    0.40
     sorrow
    0.39
    Act Density 0.000%

    No Known Activations