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

    Neuronpedia

    INDEX
    Explanations

    words related to the process of something being finished, or someone going deeply into something, possibly in a negative way.

    oai_token-act-pair · gemini-2.0-flash

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    through
    -0.88
     through
    -0.82
    expandindo
    -0.78
    Through
    -0.77
     THROUGH
    -0.77
    THROUGH
    -0.76
     Through
    -0.75
     través
    -0.71
     durch
    -0.68
     através
    -0.67
    POSITIVE LOGITS
     trying
    0.52
    нато
    0.51
     plo
    0.48
     road
    0.46
     utafitiHapana
    0.44
     tham
    0.44
     Multi
    0.43
     some
    0.43
    شل
    0.43
     problem
    0.43
    Act Density 38.196%

    No Known Activations