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

    Neuronpedia

    INDEX
    Explanations

    tons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lemon
    -0.07
     расс
    -0.06
    uin
    -0.06
    .nickname
    -0.06
    ibNameOrNil
    -0.06
    _diff
    -0.06
    .title
    -0.06
     sails
    -0.06
     Nass
    -0.06
    퓻
    -0.06
    POSITIVE LOGITS
     Recommendation
    0.08
     Ub
    0.07
    (todo
    0.07
    执法
    0.07
    هج
    0.07
    ::~
    0.07
    stdafx
    0.07
    셧
    0.06
     unab
    0.06
     psychedelic
    0.06
    Act Density 0.006%

    No Known Activations