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

    Neuronpedia

    INDEX
    Explanations

    ent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paramMap
    -0.07
    (urls
    -0.07
    .Signal
    -0.07
    _HISTORY
    -0.07
    _Con
    -0.06
     factories
    -0.06
     staffers
    -0.06
     triangles
    -0.06
    icha
    -0.06
    _encode
    -0.06
    POSITIVE LOGITS
     down
    0.06
    .int
    0.06
     ^{↵
    0.06
     berry
    0.06
    _coupon
    0.06
    ντ
    0.06
    えて
    0.06
     smarter
    0.06
    gett
    0.06
    ft
    0.06
    Act Density 0.001%

    No Known Activations