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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (background
    -0.06
     fontWeight
    -0.06
    basic
    -0.06
    anager
    -0.06
    (this
    -0.06
     себя
    -0.06
    舌
    -0.06
     ceasefire
    -0.06
     mailbox
    -0.05
    Global
    -0.05
    POSITIVE LOGITS
     Accident
    0.07
    ">&
    0.07
    .TableLayoutPanel
    0.07
            
    0.07
     lawsuit
    0.07
    -sm
    0.06
    _separator
    0.06
    سیون
    0.06
    UFACT
    0.06
     должен
    0.06
    Act Density 0.027%

    No Known Activations