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

    Neuronpedia

    INDEX
    Explanations

    technical product description

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Netflix
    -0.08
    ила
    -0.06
     byla
    -0.06
    way
    -0.06
    terr
    -0.06
    	items
    -0.06
     mua
    -0.06
    .DataGridView
    -0.06
    _CI
    -0.06
     ceased
    -0.06
    POSITIVE LOGITS
     /**
↵
    0.07
     tup
    0.06
     Craft
    0.06
     sprawling
    0.06
    VF
    0.06
     SEA
    0.06
    QUENCE
    0.06
     Kang
    0.06
     Voyager
    0.05
    Proof
    0.05
    Act Density 0.162%

    No Known Activations