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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maintenance
    -0.06
    Seg
    -0.06
    global
    -0.06
    acet
    -0.06
    ='+
    -0.06
     urgently
    -0.06
    JECTION
    -0.06
    drs
    -0.06
    _hdr
    -0.06
    (operation
    -0.06
    POSITIVE LOGITS
     cherche
    0.07
     grandfather
    0.07
    _MODEL
    0.07
     üzerine
    0.06
    ी।
    0.06
    .Boolean
    0.06
     otáz
    0.06
    rapped
    0.06
    itempty
    0.06
    فع
    0.06
    Act Density 0.012%

    No Known Activations