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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เต
    -0.07
     disrespectful
    -0.07
    _sur
    -0.07
    .KeyChar
    -0.06
    脍
    -0.06
    都能
    -0.06
     Wizards
    -0.06
    ("#{
    -0.06
     Comes
    -0.06
    שית
    -0.06
    POSITIVE LOGITS
     advisers
    0.08
    ければ
    0.08
     economist
    0.07
     foundation
    0.07
     outlook
    0.07
     kinetic
    0.07
     orderBy
    0.07
    Intermediate
    0.07
     sh
    0.07
    机构
    0.07
    Act Density 0.010%

    No Known Activations