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

    Neuronpedia

    INDEX
    Explanations

    continued

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ula
    -0.07
    ima
    -0.07
    ervention
    -0.06
    -mon
    -0.06
    ULA
    -0.06
    ipa
    -0.06
    inges
    -0.06
     considering
    -0.06
    ita
    -0.06
    CBD
    -0.06
    POSITIVE LOGITS
    TRGL
    0.07
     hWnd
    0.07
    คณะ
    0.06
    _dept
    0.06
    ="../../
    0.06
     fflush
    0.06
    '>".$
    0.06
     AssertionError
    0.06
    Memcpy
    0.06
     мяс
    0.06
    Act Density 0.020%

    No Known Activations