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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STS
    -0.07
     Chad
    -0.07
    瞬
    -0.06
     protects
    -0.06
     Step
    -0.06
    -trans
    -0.06
     Accum
    -0.06
    (Unit
    -0.06
     boldly
    -0.06
     sensors
    -0.06
    POSITIVE LOGITS
    $list
    0.07
     fury
    0.06
     )↵↵↵
    0.06
     defaultstate
    0.06
    zin
    0.06
    ิศ
    0.06
    unj
    0.06
     perseverance
    0.06
     lur
    0.06
    ikki
    0.06
    Act Density 0.013%

    No Known Activations