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

    Neuronpedia

    INDEX
    Explanations

    isper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    竜
    -0.07
    oř
    -0.06
    ůr
    -0.06
    Regs
    -0.06
     Sleeve
    -0.06
    (ln
    -0.06
     logo
    -0.06
    aku
    -0.06
    REAK
    -0.06
     Jurassic
    -0.06
    POSITIVE LOGITS
    دیگر
    0.07
    렸
    0.06
    0.06
    apse
    0.06
    同时
    0.06
    ｝
    0.06
     agree
    0.06
    んだ
    0.06
    `.`
    0.06
    合格
    0.06
    Act Density 0.087%

    No Known Activations