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
    aravel
    -0.07
     usable
    -0.07
     거의
    -0.06
    ريم
    -0.06
    ehicle
    -0.06
    quee
    -0.06
    .Members
    -0.06
     correctamente
    -0.06
    Fail
    -0.06
    -headed
    -0.06
    POSITIVE LOGITS
     obstacles
    0.06
     Theodore
    0.06
     discusses
    0.06
    '>$
    0.06
     Cipher
    0.06
     politicians
    0.06
     Τι
    0.06
    ReturnType
    0.06
    /action
    0.06
     tỉnh
    0.06
    Act Density 0.086%

    No Known Activations