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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ITICAL
    -0.06
    -tm
    -0.06
     keywords
    -0.06
     NUIT
    -0.06
    rbrakk
    -0.06
     Materials
    -0.06
     TNT
    -0.06
    ！」↵↵
    -0.06
    clin
    -0.06
     symbolic
    -0.06
    POSITIVE LOGITS
     قر
    0.07
    irq
    0.07
     nét
    0.06
    羊
    0.06
    .lng
    0.06
    ̀
    0.06
    mis
    0.06
    upply
    0.06
     insomnia
    0.06
     eden
    0.06
    Act Density 0.044%

    No Known Activations