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

    Neuronpedia

    INDEX
    Explanations

    V

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .COL
    -0.07
    aseline
    -0.07
    ihar
    -0.06
     kurtul
    -0.06
     gắng
    -0.06
    ccoli
    -0.06
    erc
    -0.06
    ldap
    -0.06
    이크
    -0.06
     ='
    -0.06
    POSITIVE LOGITS
    Vs
    0.07
    帝
    0.06
    V
    0.06
    稱
    0.06
    věd
    0.06
    ve
    0.06
     inters
    0.06
     warranted
    0.06
     ovarian
    0.06
     Ricky
    0.06
    Act Density 0.001%

    No Known Activations