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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conan
    -0.07
    aremos
    -0.06
     �
    -0.06
     dermat
    -0.06
     Panama
    -0.06
     Maryland
    -0.06
     ALS
    -0.06
    numeric
    -0.06
     ions
    -0.06
    archs
    -0.06
    POSITIVE LOGITS
     {}↵
    0.07
    yleft
    0.07
    HasBeenSet
    0.07
    。你
    0.07
    (coord
    0.07
     cfg
    0.06
     Copp
    0.06
    _SUCCESS
    0.06
    	action
    0.06
     setColor
    0.06
    Act Density 0.001%

    No Known Activations