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

    Neuronpedia

    INDEX
    Explanations

    Code, quotes, or discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wary
    -0.08
    -feed
    -0.07
    	glut
    -0.06
    subst
    -0.06
    -forward
    -0.06
    UT
    -0.06
    672
    -0.06
    _RANK
    -0.06
     menacing
    -0.06
    -redux
    -0.06
    POSITIVE LOGITS
     LOWER
    0.07
    utenant
    0.06
     詳細
    0.06
    CLASS
    0.06
     STATES
    0.06
    isoft
    0.06
     NPC
    0.06
     kk
    0.06
    궁
    0.06
    视频
    0.06
    Act Density 0.103%

    No Known Activations