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

    Neuronpedia

    INDEX
    Explanations

    psychographics and psychological terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    1.49
    i
    1.47
    ai
    1.36
    un
    1.29
    ap
    1.26
    ens
    1.23
    مان
    1.21
    اً
    1.20
    ig
    1.20
    ag
    1.19
    POSITIVE LOGITS
     on
    1.49
     одном
    1.20
     אחד
    1.16
     essayer
    1.14
    ᱔
    1.11
    ༠
    1.09
    𝟬
    1.09
    お金
    1.06
    お届け
    1.06
     chock
    1.05
    Act Density 0.015%

    No Known Activations