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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -second
    -0.07
    らの
    -0.07
     misdemeanor
    -0.07
    Cho
    -0.07
     Lite
    -0.06
    employees
    -0.06
     mulheres
    -0.06
    shipping
    -0.06
    .Direction
    -0.06
    shouldReceive
    -0.06
    POSITIVE LOGITS
    posables
    0.06
    Важ
    0.06
    ux
    0.06
     휴
    0.06
     arsch
    0.06
     wg
    0.06
    pun
    0.06
     flesh
    0.06
    etri
    0.06
    <meta
    0.06
    Act Density 0.021%

    No Known Activations