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

    Neuronpedia

    INDEX
    Explanations

    projects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fold
    -0.07
    storms
    -0.07
     ascend
    -0.07
     vowed
    -0.07
     Lor
    -0.07
    uples
    -0.06
    Pairs
    -0.06
    VECTOR
    -0.06
    	names
    -0.06
    wise
    -0.06
    POSITIVE LOGITS
    规格
    0.07
     recomm
    0.07
    悚
    0.07
     המשתמש
    0.07
    ーター
    0.07
     unavailable
    0.07
    改建
    0.06
     Website
    0.06
    executable
    0.06
     Today
    0.06
    Act Density 0.101%

    No Known Activations