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

    Neuronpedia

    INDEX
    Explanations

    Excerpts from larger works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LP
    -0.07
     Terrorism
    -0.07
    (|
    -0.06
     avenues
    -0.06
    ]
↵
    -0.06
     Former
    -0.06
    	with
    -0.06
    jte
    -0.06
    Ta
    -0.06
     formally
    -0.06
    POSITIVE LOGITS
     Stam
    0.06
     بی
    0.06
    <View
    0.06
    .comboBox
    0.06
    .checkBox
    0.06
     모르
    0.06
    _FAR
    0.06
    \CMS
    0.06
     บร
    0.06
    -binary
    0.06
    Act Density 0.026%

    No Known Activations