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

    Neuronpedia

    INDEX
    Explanations

    fitting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ptrs
    -0.06
    .Chrome
    -0.06
    	stack
    -0.06
    byss
    -0.06
    )/
    -0.06
    ën
    -0.06
     Webseite
    -0.06
     Shaft
    -0.06
    吾
    -0.06
    Cpp
    -0.06
    POSITIVE LOGITS
    Court
    0.07
    _REMOVE
    0.07
     detain
    0.07
     uncon
    0.06
     должно
    0.06
    patient
    0.06
     hilarious
    0.06
     posterior
    0.06
     dung
    0.06
    人口
    0.06
    Act Density 0.014%

    No Known Activations