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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CString
    -0.07
    972
    -0.07
    urma
    -0.06
     năng
    -0.06
     PF
    -0.06
    mts
    -0.06
     concealed
    -0.06
    ither
    -0.06
    菌
    -0.06
    阳
    -0.06
    POSITIVE LOGITS
     حالة
    0.06
     Serbian
    0.06
    .image
    0.06
     freeze
    0.06
     }↵↵↵
    0.06
     leuk
    0.06
    -frequency
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
     reopening
    0.06
    quiry
    0.06
    Act Density 0.390%

    No Known Activations