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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avoided
    -0.07
     roky
    -0.07
    cers
    -0.07
     melanch
    -0.07
    сього
    -0.07
     cms
    -0.06
     powered
    -0.06
     predomin
    -0.06
    COMPARE
    -0.06
     Об
    -0.06
    POSITIVE LOGITS
     tribal
    0.06
    ды
    0.06
     갤로그로
    0.06
     unilateral
    0.06
    资金
    0.06
    Flip
    0.06
     Npgsql
    0.06
    Ë
    0.06
    ansa
    0.05
    INY
    0.05
    Act Density 0.000%

    No Known Activations