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

    Neuronpedia

    INDEX
    Explanations

    Submitted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     workplaces
    -0.07
    _placement
    -0.06
     attends
    -0.06
     commentary
    -0.06
    _student
    -0.06
     backpage
    -0.06
     bacheca
    -0.06
     Α
    -0.06
    _detalle
    -0.06
    ));
↵
↵
    -0.06
    POSITIVE LOGITS
    (conn
    0.08
     indebted
    0.07
    Kit
    0.06
    训
    0.06
    ichen
    0.06
     sensitivity
    0.06
     comput
    0.06
    sub
    0.06
    spl
    0.06
     requ
    0.06
    Act Density 0.003%

    No Known Activations