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

    Neuronpedia

    INDEX
    Explanations

    product pages and consumer electronics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     literally
    0.39
    绿色
    0.39
     literal
    0.39
     பச்சை
    0.38
     singoli
    0.38
     ilust
    0.38
    洟
    0.38
     DMP
    0.37
    eiro
    0.37
     কিলো
    0.37
    POSITIVE LOGITS
    CHEMY
    0.43
    哲学
    0.42
    putable
    0.42
    放棄
    0.42
    éns
    0.40
    ophagy
    0.39
     Blogging
    0.39
    自己
    0.38
    Philosophy
    0.38
    放弃
    0.37
    Act Density 0.002%

    No Known Activations