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

    Neuronpedia

    INDEX
    Explanations

    Shared attributes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /js
    -0.06
    ACLE
    -0.06
    Mex
    -0.06
    roduction
    -0.06
     клуб
    -0.06
    ン�
    -0.06
    är
    -0.06
    SUB
    -0.06
     hus
    -0.05
     condemn
    -0.05
    POSITIVE LOGITS
     RVA
    0.07
    .two
    0.07
    .binding
    0.06
    /red
    0.06
     speakers
    0.06
    	getline
    0.06
     Congratulations
    0.06
    _REMOTE
    0.06
     Also
    0.06
    EditingController
    0.06
    Act Density 0.019%

    No Known Activations