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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	top
    -0.07
    today
    -0.07
    password
    -0.07
    Fake
    -0.07
    ecurity
    -0.07
    change
    -0.07
    callbacks
    -0.06
    micro
    -0.06
     support
    -0.06
     waterfront
    -0.06
    POSITIVE LOGITS
     процессе
    0.07
    ogens
    0.06
    ्ष
    0.06
    .addComponent
    0.06
    &w
    0.06
    (datas
    0.06
    ogen
    0.06
    _child
    0.06
     Jihad
    0.06
    .FormattingEnabled
    0.06
    Act Density 0.131%

    No Known Activations