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

    Neuronpedia

    INDEX
    Explanations

    asis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Royal
    -0.06
    HttpPost
    -0.06
    argent
    -0.06
     Burke
    -0.06
     Megan
    -0.06
     worden
    -0.06
    ]+
    -0.06
     repent
    -0.06
    -league
    -0.06
     Most
    -0.06
    POSITIVE LOGITS
     dlg
    0.08
    entina
    0.07
    asis
    0.07
     consumes
    0.07
    Trigger
    0.07
    !!!↵↵
    0.06
     stash
    0.06
    NESS
    0.06
     ปร
    0.06
     Sanctuary
    0.06
    Act Density 0.002%

    No Known Activations