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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hran
    -0.07
     Hal
    -0.07
    působ
    -0.06
     altre
    -0.06
     Cel
    -0.06
     パ
    -0.06
     plán
    -0.06
    _reaction
    -0.06
    	Http
    -0.06
    γκα
    -0.06
    POSITIVE LOGITS
    99
    0.07
    025
    0.06
    Fuel
    0.06
     kafka
    0.06
    device
    0.06
    ////////////////////////////////////////////////////////////////////////////////↵↵
    0.06
     ischem
    0.06
     ask
    0.06
    	match
    0.06
    ец
    0.06
    Act Density 0.000%

    No Known Activations