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

    Neuronpedia

    INDEX
    Explanations

    etcetera

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pwd
    -0.08
     robber
    -0.07
     toddler
    -0.07
     visibly
    -0.07
    	size
    -0.06
     EXIT
    -0.06
     ře
    -0.06
     CREATE
    -0.06
    .create
    -0.06
     Belle
    -0.06
    POSITIVE LOGITS
    xD
    0.08
     etc
    0.07
     Sprint
    0.06
    /class
    0.06
     Invocation
    0.06
     등
    0.06
    ("?
    0.06
    asks
    0.06
     formations
    0.06
     bin
    0.06
    Act Density 0.016%

    No Known Activations