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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pes
    -0.07
    ased
    -0.07
     Tf
    -0.07
     tôn
    -0.07
    簽
    -0.07
    主线
    -0.06
     Vacuum
    -0.06
    uced
    -0.06
    妹
    -0.06
     esac
    -0.06
    POSITIVE LOGITS
    Playback
    0.08
     الحرب
    0.07
    钴
    0.07
     sophomore
    0.07
    flags
    0.07
    .putExtra
    0.06
    瑞士
    0.06
    เตร
    0.06
    .moveTo
    0.06
    잴
    0.06
    Act Density 0.075%

    No Known Activations