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

    Neuronpedia

    INDEX
    Explanations

    Technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .af
    -0.07
    Stat
    -0.06
    bundle
    -0.06
    poi
    -0.06
    cede
    -0.06
    locked
    -0.06
     lis
    -0.06
     �
    -0.06
     personally
    -0.06
    Women
    -0.06
    POSITIVE LOGITS
    .task
    0.07
    �
    0.07
    вся
    0.06
    54
    0.06
     учнів
    0.06
     hypoth
    0.06
     hogy
    0.06
    ächst
    0.06
     đạo
    0.06
    ной
    0.06
    Act Density 0.296%

    No Known Activations