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

    Neuronpedia

    INDEX
    Explanations

    proper names and titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mâ
    -0.25
    None
    -0.25
    çIJĨæĥ³çļĦ
    -0.25
    Subject
    -0.24
     Reich
    -0.24
    *dt
    -0.24
    çĪ±ä½ł
    -0.24
    sse
    -0.23
    arget
    -0.23
    eron
    -0.23
    POSITIVE LOGITS
    vern
    0.28
    validators
    0.27
    ounter
    0.26
    æijĩ
    0.26
    nesia
    0.26
    å¿ĥ
    0.25
    蹦
    0.25
     sher
    0.25
    inds
    0.25
    æIJĸ
    0.25
    Act Density 0.002%

    No Known Activations