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

    Neuronpedia

    INDEX
    Explanations

    agent sequence AutoGPT babyAGI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Just
    0.44
    Cape
    0.42
    Kim
    0.41
    0.41
    Sir
    0.41
    Simply
    0.40
    Want
    0.39
    First
    0.38
    Lord
    0.38
    Have
    0.38
    POSITIVE LOGITS
    燵
    0.41
     forested
    0.40
     Glast
    0.39
    ಿದ
    0.38
     hag
    0.38
    atars
    0.38
     navigable
    0.38
     glTexCoord
    0.37
     `-
    0.37
     partant
    0.37
    Act Density 0.001%

    No Known Activations