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

    Neuronpedia

    INDEX
    Explanations

    DIRECT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝑯
    -0.08
    赶上
    -0.07
    켬
    -0.07
    넸
    -0.07
    aho
    -0.07
     strapon
    -0.07
     inex
    -0.07
     Aside
    -0.07
    PROC
    -0.07
    跑到
    -0.07
    POSITIVE LOGITS
     Democrats
    0.07
    ิก
    0.07
    潮
    0.06
    וצר
    0.06
    ogs
    0.06
    တ
    0.06
     di
    0.06
     SOME
    0.06
     forming
    0.06
     cải
    0.06
    Act Density 0.000%

    No Known Activations