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

    Neuronpedia

    INDEX
    Explanations

    hiding user interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ligação
    -0.08
     relacionamento
    -0.08
     localização
    -0.08
     condit
    -0.08
    (cookie
    -0.08
     liaison
    -0.08
    Debit
    -0.07
     softness
    -0.07
     EMAIL
    -0.07
    tie
    -0.07
    POSITIVE LOGITS
    .hide
    0.11
    hide
    0.10
     distractions
    0.10
    toolbar
    0.10
    Toolbar
    0.10
    -hide
    0.10
     hide
    0.10
    	hide
    0.10
     hiding
    0.10
     убрать
    0.09
    Act Density 0.005%

    No Known Activations