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

    Neuronpedia

    INDEX
    Explanations

    java package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hydrochloride
    0.45
    🔳
    0.44
    欱
    0.43
     ferrugineux
    0.43
     乾燥
    0.42
    𒉆
    0.41
    ಂದರೆ
    0.41
     Hydrochloride
    0.40
     OXIDES
    0.40
    酊
    0.40
    POSITIVE LOGITS
     J
    0.54
    G
    0.54
    un
    0.54
    S
    0.52
    c
    0.51
    f
    0.51
    j
    0.51
    K
    0.51
    us
    0.50
    ac
    0.48
    Act Density 0.001%

    No Known Activations