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

    Neuronpedia

    INDEX
    Explanations

    debugging code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pursuit
    -0.08
     chilli
    -0.08
     strict
    -0.08
     sublim
    -0.08
     chili
    -0.08
    Acceptance
    -0.07
     subsid
    -0.07
    严格
    -0.07
     comedic
    -0.07
     propria
    -0.07
    POSITIVE LOGITS
     Variables
    0.09
     телефона
    0.09
     snapshot
    0.09
     Dumps
    0.09
     informações
    0.09
     крови
    0.09
     Informationen
    0.08
     dump
    0.08
    snapshot
    0.08
    .INFO
    0.08
    Act Density 0.004%

    No Known Activations