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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deposit
    -0.08
     auxiliary
    -0.08
    Stake
    -0.07
     aux
    -0.07
     motor
    -0.07
    ’da
    -0.07
     deliver
    -0.07
    団
    -0.07
     scalar
    -0.07
     inj
    -0.07
    POSITIVE LOGITS
    ារ�
    0.09
    _CODES
    0.09
    _SIM
    0.09
     собственной
    0.09
     Осы
    0.08
     ;-)↵↵
    0.08
     สล็อตออนไลน์
    0.08
    uintptr
    0.08
     ;)↵
    0.08
     geeks
    0.08
    Act Density 0.149%

    No Known Activations