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

    Neuronpedia

    INDEX
    Explanations

    Software development requirements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     competing
    -0.08
     OPTION
    -0.08
    "B
    -0.07
    录
    -0.07
     Politics
    -0.07
    called
    -0.07
     alleging
    -0.07
    ERM
    -0.07
     additives
    -0.07
     american
    -0.06
    POSITIVE LOGITS
    _FRONT
    0.06
    診
    0.06
     코
    0.06
     حرفه
    0.06
    _blob
    0.06
     กรกฎาคม
    0.06
    (cancel
    0.06
    �
    0.06
     شما
    0.06
    .YesNo
    0.06
    Act Density 0.157%

    No Known Activations