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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    foobar
    -0.09
    Ｌ
    -0.07
     COMMIT
    -0.07
    irable
    -0.07
    лой
    -0.06
    (filePath
    -0.06
    }↵↵↵↵
    -0.06
    (expect
    -0.06
     ""
↵
    -0.06
    FALSE
    -0.06
    POSITIVE LOGITS
     referred
    0.07
     sat
    0.07
    et
    0.07
    den
    0.07
    det
    0.06
     kick
    0.06
    	Set
    0.06
     established
    0.06
    rep
    0.06
     contained
    0.06
    Act Density 0.005%

    No Known Activations