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

    Neuronpedia

    INDEX
    Explanations

    Unusual characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _assignment
    -0.07
     targeting
    -0.07
    �
    -0.06
     empirical
    -0.06
     study
    -0.06
    -->
    -0.06
     Setter
    -0.06
     "%.
    -0.06
    ほう
    -0.06
    .lst
    -0.06
    POSITIVE LOGITS
    ической
    0.07
    Michigan
    0.07
    bdd
    0.06
    0.06
     sqlCommand
    0.06
     Michigan
    0.06
    /net
    0.06
     publik
    0.06
     покол
    0.06
     SQL
    0.06
    Act Density 0.002%

    No Known Activations