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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )y
    -0.07
    Viol
    -0.07
     multiprocessing
    -0.07
    ме
    -0.06
    Hints
    -0.06
    ACES
    -0.06
    Eb
    -0.06
     tienes
    -0.06
    	conf
    -0.06
    .conf
    -0.06
    POSITIVE LOGITS
    File
    0.07
    Qed
    0.06
    /control
    0.06
     Balt
    0.06
    อล
    0.06
     fak
    0.06
     err
    0.06
     Osw
    0.06
     Wash
    0.06
     tussen
    0.06
    Act Density 0.008%

    No Known Activations