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

    Neuronpedia

    INDEX
    Explanations

    correspond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    correspond
    -1.64
     Correspond
    -1.55
     correspond
    -1.54
    corresponding
    -1.53
     correspondent
    -1.51
     CORRESPOND
    -1.48
     corresponding
    -1.42
     corrispond
    -1.42
    Correspond
    -1.40
     corresponded
    -1.37
    POSITIVE LOGITS
     to
    0.73
     with
    0.52
     rapat
    0.47
    pea
    0.47
    olver
    0.46
    чо
    0.46
    טור
    0.46
    ņ
    0.46
    a
    0.45
    bes
    0.43
    Act Density 0.200%

    No Known Activations