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

    Neuronpedia

    INDEX
    Explanations

    existential concepts and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ре
    1.33
    。
    1.29
    ен
    1.24
    。【
    1.23
    )。
    1.22
    。<
    1.20
    。“
    1.19
    し
    1.19
    arı
    1.16
    ି
    1.16
    POSITIVE LOGITS
    ue
    1.23
    </h2>
    1.12
    nya
    1.12
    u
    1.09
    ल
    1.09
    ↵↵
    1.05
    ac
    1.03
    ib
    1.02
    UR
    1.01
     premiere
    0.99
    Act Density 0.126%

    No Known Activations