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

    Neuronpedia

    INDEX
    Explanations

    potential for action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protocols
    0.40
     registries
    0.40
     registry
    0.39
    还没有
    0.39
     variante
    0.39
    叕
    0.39
     Magist
    0.38
     Venezuel
    0.38
     sutures
    0.37
     Protocols
    0.37
    POSITIVE LOGITS
    Expired
    0.44
     unspoken
    0.42
     Horses
    0.41
     heavy
    0.38
     apreciar
    0.38
     formed
    0.38
     कथित
    0.37
    пол
    0.36
     muñ
    0.36
     poté
    0.36
    Act Density 0.005%

    No Known Activations