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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ర్ల
    -0.07
     pursuant
    -0.07
    ಿತ
    -0.07
     differs
    -0.07
    etek
    -0.07
     finances
    -0.07
     tones
    -0.07
    Ticks
    -0.07
    -0.07
    ర్లు
    -0.07
    POSITIVE LOGITS
    भार
    0.09
    όν
    0.08
     unst
    0.08
    幅
    0.07
    所属
    0.07
     overst
    0.07
    质量
    0.07
     કાર્ય
    0.07
     अन
    0.07
     અન
    0.07
    Act Density 0.005%
    No Known Activations