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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sys
    -0.07
    ۳۰
    -0.07
     Ctrl
    -0.06
     Při
    -0.06
    ]["
    -0.06
    	Model
    -0.06
     ราย
    -0.06
    fixtures
    -0.06
    .hasOwnProperty
    -0.06
    _chr
    -0.06
    POSITIVE LOGITS
    Advertising
    0.08
     rg
    0.07
     surpr
    0.07
     APPLICATION
    0.06
    -values
    0.06
     trademark
    0.06
    胞
    0.06
     inhibitors
    0.06
    /live
    0.06
    Solution
    0.06
    Act Density 0.034%

    No Known Activations