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

    Neuronpedia

    INDEX
    Explanations

    allies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     goodbye
    -0.07
     alo
    -0.07
    .video
    -0.06
    (Member
    -0.06
     YOUR
    -0.06
    _redirected
    -0.06
    (light
    -0.06
    私の
    -0.06
    ;?#
    -0.06
    _material
    -0.06
    POSITIVE LOGITS
     Ref
    0.07
    idelberg
    0.07
     kalk
    0.07
    kept
    0.06
    Json
    0.06
    važ
    0.06
     coworkers
    0.06
     mö
    0.06
    anch
    0.06
     Mit
    0.06
    Act Density 0.027%

    No Known Activations