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

    Neuronpedia

    INDEX
    Explanations

    noun followed by specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Di
    0.43
    STA
    0.40
     war
    0.39
     agre
    0.39
     position
    0.37
     individual
    0.37
    xn
    0.37
    发生的
    0.37
    S
    0.36
     localized
    0.36
    POSITIVE LOGITS
    ёма
    0.42
     Semua
    0.40
    一郎
    0.40
    資金
    0.38
     všech
    0.38
    ശ്വാ
    0.38
     ಶಿವ
    0.38
     三菱
    0.38
    ഹി
    0.37
     షో
    0.37
    Act Density 0.000%

    No Known Activations