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

    Neuronpedia

    INDEX
    Explanations

    housing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ide
    -0.07
    验证码
    -0.07
    	Delete
    -0.07
    [end
    -0.07
     campo
    -0.06
     Buch
    -0.06
    .CASCADE
    -0.06
    _factors
    -0.06
    -ended
    -0.06
    _CHANGE
    -0.06
    POSITIVE LOGITS
     intestine
    0.06
     vyk
    0.06
     край
    0.06
     wrapped
    0.06
    ******
↵
    0.06
     Assistant
    0.06
    _CNTL
    0.06
     boundary
    0.06
     uvád
    0.06
     движ
    0.06
    Act Density 0.023%

    No Known Activations