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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pestic
    -0.08
     butcher
    -0.08
    >C
    -0.07
     tenga
    -0.07
     leaving
    -0.07
    صال
    -0.07
     Conc
    -0.07
     rfl
    -0.07
     VLC
    -0.07
     Needs
    -0.07
    POSITIVE LOGITS
    高的
    0.07
     payload
    0.07
    LoggedIn
    0.07
    Analysis
    0.07
    Summary
    0.06
    ภ
    0.06
    ,data
    0.06
     regulators
    0.06
    _variables
    0.06
    模拟
    0.06
    Act Density 0.014%

    No Known Activations