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

    Neuronpedia

    INDEX
    Explanations

    six

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Br
    -0.07
    一阵
    -0.07
     OCT
    -0.07
    	RE
    -0.06
    רון
    -0.06
     MSR
    -0.06
     forb
    -0.06
    ❕
    -0.06
    ho
    -0.06
     Ranger
    -0.06
    POSITIVE LOGITS
     six
    0.08
    aic
    0.07
    _deriv
    0.07
     exploit
    0.07
    骸
    0.07
    明确了
    0.07
    6
    0.07
     lập
    0.07
    ここ
    0.07
    ていきたい
    0.07
    Act Density 0.166%

    No Known Activations