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

    Neuronpedia

    INDEX
    Explanations

    normal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lak
    -0.08
    aud
    -0.07
     où
    -0.07
     au
    -0.06
     food
    -0.06
     iddi
    -0.06
     bás
    -0.06
    ôme
    -0.06
     potrze
    -0.06
    WW
    -0.06
    POSITIVE LOGITS
    ida
    0.07
    }`)↵
    0.06
     mixes
    0.06
     decre
    0.06
     Garmin
    0.06
     Massive
    0.06
     woodworking
    0.06
    terrorism
    0.06
    	dest
    0.06
     HelloWorld
    0.06
    Act Density 0.069%

    No Known Activations