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

    Neuronpedia

    INDEX
    Explanations

    of the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /**
    -0.08
    /**↵
    -0.07
     hour
    -0.07
     room
    -0.07
    (<
    -0.07
     oci
    -0.06
     corridors
    -0.06
     ministers
    -0.06
     Daniel
    -0.06
     Freed
    -0.06
    POSITIVE LOGITS
     uvád
    0.06
     Actor
    0.06
    .awtextra
    0.06
    .InnerException
    0.06
    销
    0.06
    _mini
    0.06
    Bindings
    0.06
    validator
    0.06
    vements
    0.06
     엄
    0.06
    Act Density 0.031%

    No Known Activations