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

    Neuronpedia

    INDEX
    Explanations

    assistance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wiser
    -0.09
    ្គ
    -0.08
     একটা
    -0.08
    -0.08
     maximize
    -0.08
     Sandbox
    -0.08
    ತನ
    -0.08
     essência
    -0.08
     bers
    -0.08
    ически
    -0.08
    POSITIVE LOGITS
     especially
    0.09
    ในการ
    0.09
    ociate
    0.08
    .Convert
    0.08
    ments
    0.08
    iliary
    0.07
    imate
    0.07
     during
    0.07
    ively
    0.07
    reply
    0.07
    Act Density 0.014%
    No Known Activations