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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    证明
    -0.07
    ीं,
    -0.06
     stehen
    -0.06
    erval
    -0.06
     cười
    -0.06
    _,
    -0.06
    Checksum
    -0.06
    seys
    -0.06
    bew
    -0.06
    POSITIVE LOGITS
     or
    0.10
     &
    0.09
     and
    0.09
     Or
    0.08
     AND
    0.07
     OR
    0.07
     Trad
    0.07
     D
    0.07
     And
    0.07
    and
    0.06
    Act Density 0.428%

    No Known Activations