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

    Neuronpedia

    INDEX
    Explanations

    say "made"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Item
    -0.07
    Clients
    -0.06
    <Item
    -0.06
     xảy
    -0.06
     光
    -0.06
     interrogation
    -0.06
     �
    -0.06
    kin
    -0.06
     Vall
    -0.06
    ilded
    -0.06
    POSITIVE LOGITS
    edar
    0.06
     IRC
    0.06
     maintains
    0.06
    /../
    0.06
    gres
    0.06
    /jquery
    0.06
    ssl
    0.06
    graded
    0.06
    mtree
    0.06
     крок
    0.06
    Act Density 0.164%

    No Known Activations