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

    Neuronpedia

    INDEX
    Explanations

    connections and standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prototype
    0.43
     EAC
    0.43
     CAMP
    0.40
     Hei
    0.38
    CAMP
    0.37
     Generated
    0.36
     GMO
    0.36
     narrated
    0.36
     Blast
    0.36
     tre
    0.36
    POSITIVE LOGITS
    fon
    0.39
     connexion
    0.39
    steering
    0.39
    tugraz
    0.38
    brushes
    0.37
    atlan
    0.37
     suppressing
    0.36
     conexão
    0.36
     связь
    0.36
    یدن
    0.36
    Act Density 0.000%

    No Known Activations