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

    Neuronpedia

    INDEX
    Explanations

    responsibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .travel
    -0.07
    978
    -0.06
    Cİ
    -0.06
     hấp
    -0.06
    Lost
    -0.06
    _DIG
    -0.06
    993
    -0.06
     '..',
    -0.06
     encompasses
    -0.06
    방송
    -0.06
    POSITIVE LOGITS
    MF
    0.07
     mosquito
    0.07
     movements
    0.07
     Arbor
    0.07
     comments
    0.06
     invest
    0.06
    roach
    0.06
     HK
    0.06
     awesome
    0.06
    office
    0.06
    Act Density 0.014%

    No Known Activations