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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pants
    -0.07
    .trailingAnchor
    -0.07
    _limits
    -0.07
     продукт
    -0.06
    _sizes
    -0.06
    [indexPath
    -0.06
     chatt
    -0.06
    вав
    -0.06
    =color
    -0.06
     hogy
    -0.06
    POSITIVE LOGITS
     hatte
    0.06
    SHARE
    0.06
    	pc
    0.06
    ीसर
    0.06
    ़
    0.06
    rible
    0.06
    erry
    0.06
    .)↵
    0.06
    -Time
    0.06
     Cinder
    0.06
    Act Density 0.011%

    No Known Activations