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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -budget
    -0.07
     Iranian
    -0.07
     frightened
    -0.06
    /animate
    -0.06
     Coding
    -0.06
    iado
    -0.06
    .Products
    -0.06
    pest
    -0.06
     Susp
    -0.06
     slave
    -0.06
    POSITIVE LOGITS
     """
↵
    0.07
    άκ
    0.06
    ีค
    0.06
    альный
    0.06
     присутств
    0.06
    vr
    0.06
    alloca
    0.06
    ул
    0.06
    är
    0.06
     StyleSheet
    0.06
    Act Density 0.004%

    No Known Activations