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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boy
    -0.07
     ordered
    -0.07
     Civ
    -0.07
    radio
    -0.07
     Server
    -0.07
     vin
    -0.06
     underwater
    -0.06
    group
    -0.06
    left
    -0.06
     adults
    -0.06
    POSITIVE LOGITS
     розвиток
    0.07
    _REALTYPE
    0.07
     �
    0.07
    Maintenance
    0.06
    ebi
    0.06
     ****************************************
    0.06
    кие
    0.06
     самост
    0.06
     lessen
    0.06
    $t
    0.06
    Act Density 0.019%

    No Known Activations