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

    Neuronpedia

    INDEX
    Explanations

    ladder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    authenticate
    -0.29
    enci
    -0.26
     abundance
    -0.25
    ä¹°çļĦ
    -0.25
    decision
    -0.24
    .authenticate
    -0.24
    Aaron
    -0.23
    abe
    -0.23
    baugh
    -0.23
    habi
    -0.23
    POSITIVE LOGITS
    estruct
    0.28
    IMO
    0.26
    orny
    0.26
    imum
    0.25
    enet
    0.25
    çĵ£
    0.25
    ém
    0.25
    lett
    0.24
     parent
    0.24
    è½®æµģ
    0.24
    Act Density 0.142%

    No Known Activations