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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    n
    -0.07
    stacle
    -0.07
     Odd
    -0.07
     黑
    -0.07
     Approach
    -0.07
     doğrudan
    -0.06
    ัปดาห
    -0.06
    後の
    -0.06
    auction
    -0.06
    igth
    -0.06
    POSITIVE LOGITS
     Emb
    0.08
     expressive
    0.07
    mq
    0.06
    eq
    0.06
    isposable
    0.06
    _VOID
    0.06
     °
    0.06
    Adv
    0.06
    fonts
    0.06
     ruthless
    0.06
    Act Density 0.004%

    No Known Activations