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

    Neuronpedia

    INDEX
    Explanations

    2x2 tables, statistical analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     Knife
    -0.06
     Dual
    -0.06
    (jsonPath
    -0.06
    -so
    -0.06
    Aggregate
    -0.06
     krist
    -0.06
     火
    -0.06
     hostage
    -0.06
    _banner
    -0.06
    POSITIVE LOGITS
     Ö
    0.07
     Piece
    0.06
    pj
    0.06
     Bunu
    0.06
    ("").
    0.06
    แสดง
    0.06
    ิร
    0.06
    ็อก
    0.06
    maj
    0.06
    μφωνα
    0.06
    Act Density 0.141%

    No Known Activations