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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	dist
    -0.07
    .between
    -0.07
    /place
    -0.07
    .uint
    -0.07
    egend
    -0.07
     at
    -0.07
     native
    -0.07
    /r
    -0.06
    on
    -0.06
    	org
    -0.06
    POSITIVE LOGITS
    瘢
    0.07
    מיכה
    0.06
    投标
    0.06
    הד
    0.06
    Ⱏ
    0.06
    加盟商
    0.06
     fireplace
    0.06
    屏蔽
    0.06
    acons
    0.06
    瑨
    0.06
    Act Density 0.000%

    No Known Activations