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

    Neuronpedia

    INDEX
    Explanations

    observation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ерта
    -0.07
     scoop
    -0.06
     cart
    -0.06
     خور
    -0.06
    HEAD
    -0.06
     emp
    -0.06
     voucher
    -0.06
     IPA
    -0.06
     sufferers
    -0.06
     median
    -0.06
    POSITIVE LOGITS
    ęki
    0.07
    ToDelete
    0.07
     Vlad
    0.07
     eiusmod
    0.07
     Marble
    0.07
    bd
    0.07
    한테
    0.07
    _KEYBOARD
    0.06
    	boost
    0.06
     obviously
    0.06
    Act Density 0.008%

    No Known Activations