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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Preferred
    -0.07
     new
    -0.06
     Shiv
    -0.06
    ruc
    -0.06
    	new
    -0.06
    (re
    -0.06
     Bad
    -0.06
    .matcher
    -0.06
    _xs
    -0.06
     performs
    -0.06
    POSITIVE LOGITS
     notch
    0.07
    Clipboard
    0.07
    ppelin
    0.07
    422
    0.07
    dob
    0.06
    сього
    0.06
     milano
    0.06
    inin
    0.06
     createdAt
    0.06
    	Mono
    0.06
    Act Density 0.003%

    No Known Activations