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

    Neuronpedia

    INDEX
    Explanations

    literary awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ob
    -0.07
    ordinated
    -0.06
    ollection
    -0.06
    @Service
    -0.06
    LAB
    -0.06
    ppo
    -0.06
    \Container
    -0.06
    HEEL
    -0.06
     prose
    -0.06
    .inverse
    -0.06
    POSITIVE LOGITS
    κι
    0.07
    (validation
    0.07
    ([]);↵↵
    0.07
    ()].
    0.07
     서울
    0.06
     graphene
    0.06
    (panel
    0.06
    DockControl
    0.06
     tóc
    0.06
    As
    0.06
    Act Density 0.004%

    No Known Activations