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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เห
    -0.08
     开始
    -0.07
     kterého
    -0.07
     تغییر
    -0.07
     intimid
    -0.06
    ありがとう
    -0.06
     İŞ
    -0.06
     MSS
    -0.06
     이야
    -0.06
    sad
    -0.06
    POSITIVE LOGITS
     beberapa
    0.07
     recently
    0.07
    opus
    0.07
     removal
    0.06
    Membership
    0.06
    angu
    0.06
     erotische
    0.06
    (userInfo
    0.06
    /,↵
    0.06
     fixes
    0.06
    Act Density 0.007%

    No Known Activations