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

    Neuronpedia

    INDEX
    Explanations

    worship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     delays
    -0.07
    53
    -0.07
    dělen
    -0.07
    lied
    -0.06
     amort
    -0.06
     timelines
    -0.06
     timeline
    -0.06
    .LINE
    -0.06
     sets
    -0.06
     depressing
    -0.06
    POSITIVE LOGITS
     worship
    0.18
     Worship
    0.14
     worsh
    0.11
     Wor
    0.10
     wor
    0.09
     Witness
    0.07
     fellowship
    0.07
    &W
    0.07
     Yoshi
    0.07
    προ
    0.07
    Act Density 0.003%

    No Known Activations