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

    Neuronpedia

    INDEX
    Explanations

    radio airplay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     york
    -0.07
    Tree
    -0.07
    	cache
    -0.07
    Alg
    -0.06
    átní
    -0.06
    finish
    -0.06
     bik
    -0.06
     Id
    -0.06
     ara
    -0.06
    udio
    -0.06
    POSITIVE LOGITS
    <?=
    0.07
    輸
    0.07
    AJOR
    0.06
    replacement
    0.06
    jíž
    0.06
    ��
    0.06
    ávis
    0.06
    vatel
    0.06
     vực
    0.06
     iff
    0.06
    Act Density 0.021%

    No Known Activations