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

    Neuronpedia

    INDEX
    Explanations

    Code and error messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coma
    -0.06
     Locked
    -0.06
    domain
    -0.06
     Ves
    -0.06
     testCase
    -0.06
    	project
    -0.06
    费用
    -0.06
     sir
    -0.06
    enerated
    -0.06
    .fromCharCode
    -0.06
    POSITIVE LOGITS
    ???↵↵
    0.07
     якому
    0.07
    ὰ
    0.07
    ольз
    0.07
     ’
    0.06
     Desc
    0.06
    _ble
    0.06
    рид
    0.06
     不
    0.06
    .softmax
    0.06
    Act Density 0.059%

    No Known Activations