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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .chrome
    -0.06
     grunt
    -0.06
    洞
    -0.06
     labour
    -0.06
     pride
    -0.06
     drunk
    -0.06
     sandwich
    -0.06
    画
    -0.06
    eous
    -0.06
    ably
    -0.06
    POSITIVE LOGITS
     RK
    0.07
    rem
    0.07
    RK
    0.06
    .nextElement
    0.06
    JD
    0.06
    üne
    0.06
    ี↵
    0.06
     MPL
    0.06
    SA
    0.06
    сом
    0.06
    Act Density 0.000%

    No Known Activations