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

    Neuronpedia

    INDEX
    Explanations

    <%=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chung
    -0.06
     autob
    -0.06
    _mutex
    -0.06
     doomed
    -0.06
    ocusing
    -0.06
    _parents
    -0.06
    territ
    -0.06
     Besch
    -0.06
     Letter
    -0.06
     başk
    -0.06
    POSITIVE LOGITS
     productos
    0.07
    OldData
    0.07
    影响
    0.07
    ึ
    0.06
    ǐ
    0.06
     Helpful
    0.06
    different
    0.06
     GF
    0.06
    .org
    0.06
     seperate
    0.06
    Act Density 0.003%

    No Known Activations