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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ALPHA
    -0.06
     Girl
    -0.06
     опис
    -0.06
    .EndsWith
    -0.06
     burge
    -0.06
     Supplements
    -0.05
     PURE
    -0.05
    develop
    -0.05
     Sunder
    -0.05
     older
    -0.05
    POSITIVE LOGITS
    .,
    0.07
     assumptions
    0.07
     týden
    0.07
    .....
    0.07
    ист
    0.06
    	ct
    0.06
    .asInstanceOf
    0.06
    .subscribe
    0.06
    .strictEqual
    0.06
     Herbert
    0.06
    Act Density 0.110%

    No Known Activations