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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ころ
    -0.07
    \Api
    -0.07
    Foot
    -0.07
    Presence
    -0.06
     ал
    -0.06
     obey
    -0.06
    cro
    -0.06
    Authenticated
    -0.06
     entrances
    -0.06
     Fun
    -0.06
    POSITIVE LOGITS
    σμα
    0.07
    .depend
    0.06
    MG
    0.06
    	NullCheck
    0.06
    vak
    0.06
    äge
    0.06
    (encoder
    0.06
    /pr
    0.06
    (sensor
    0.06
     fik
    0.06
    Act Density 0.009%

    No Known Activations