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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    problem
    -0.07
    А
    -0.07
    ]*)
    -0.07
    戰
    -0.07
    і
    -0.06
    ʊ
    -0.06
    𝕖
    -0.06
                ↵↵
    -0.06
    ө
    -0.06
    海上
    -0.06
    POSITIVE LOGITS
     Playback
    0.07
    nels
    0.07
     kayıt
    0.07
    牝
    0.07
    ยก
    0.07
    sPid
    0.07
     sadd
    0.07
     Kaz
    0.07
     DEVICE
    0.07
    くだ
    0.07
    Act Density 0.060%

    No Known Activations