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

    Neuronpedia

    INDEX
    Explanations

    left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .install
    -0.07
     интерес
    -0.07
    ob
    -0.06
     lineage
    -0.06
    .attribute
    -0.06
    这样
    -0.06
     transferred
    -0.06
     ancestors
    -0.06
    화를
    -0.06
    '])?
    -0.06
    POSITIVE LOGITS
     adaptations
    0.07
     Ry
    0.06
     Annex
    0.06
    /modal
    0.06
    좋
    0.06
    SCRIPTOR
    0.06
    elem
    0.06
    blems
    0.06
    98
    0.06
     Lux
    0.06
    Act Density 0.007%

    No Known Activations