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

    Neuronpedia

    INDEX
    Explanations

    commit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ToWorld
    -0.06
     skeptical
    -0.06
    _views
    -0.06
    (go
    -0.06
    lescope
    -0.06
     commentary
    -0.06
     matures
    -0.06
     ana
    -0.06
     TEMPLATE
    -0.06
    	pl
    -0.06
    POSITIVE LOGITS
    _XDECREF
    0.07
     Bal
    0.06
    Toy
    0.06
     Newtown
    0.06
     waitress
    0.06
     attributed
    0.06
    dan
    0.06
    ражд
    0.06
    [right
    0.06
    Assert
    0.06
    Act Density 0.210%

    No Known Activations