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

    Neuronpedia

    INDEX
    Explanations

    00

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #↵↵
    -0.07
    Dead
    -0.07
     sns
    -0.06
     Smart
    -0.06
    (types
    -0.06
    	x
    -0.06
     rsp
    -0.06
     sensory
    -0.06
    .box
    -0.06
    ，由
    -0.06
    POSITIVE LOGITS
    .DTO
    0.07
     hesab
    0.07
     �
    0.07
     승
    0.07
    づ
    0.07
    areth
    0.06
    _sep
    0.06
    VENT
    0.06
    \Models
    0.06
     UInt
    0.06
    Act Density 0.016%

    No Known Activations