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

    Neuronpedia

    INDEX
    Explanations

    inhibitors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Slayer
    -0.07
     Stored
    -0.07
    	task
    -0.07
    /mat
    -0.07
     projev
    -0.07
     역
    -0.06
     fian
    -0.06
    constitution
    -0.06
    iconductor
    -0.06
    .pb
    -0.06
    POSITIVE LOGITS
    '</
    0.07
     #↵
    0.07
     repl
    0.06
     notch
    0.06
     المهنة
    0.06
    (Environment
    0.06
    ('</
    0.06
     Scha
    0.06
     türlü
    0.06
     questionable
    0.06
    Act Density 0.005%

    No Known Activations