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

    Neuronpedia

    INDEX
    Explanations

    colon/quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    _DETECT
    -0.07
    utdown
    -0.07
     Tuesday
    -0.07
     Would
    -0.07
    _DM
    -0.07
    ith
    -0.07
     Sayı
    -0.06
     IID
    -0.06
    "',
    -0.06
    POSITIVE LOGITS
    :**
    0.11
    :[
    0.10
    :"
    0.10
    :'
    0.10
    :_
    0.09
    :
    0.09
    :http
    0.08
     confront
    0.08
    :E
    0.08
    :{
    0.08
    Act Density 0.025%

    No Known Activations