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
     widow
    -0.09
     Specifies
    -0.08
    �
    -0.08
    those
    -0.08
    那些
    -0.08
     Startup
    -0.08
    县
    -0.07
     specifies
    -0.07
     membre
    -0.07
     sorties
    -0.07
    POSITIVE LOGITS
     suspicion
    0.09
     света
    0.09
     sospe
    0.09
     Heinz
    0.08
     sly
    0.08
     Guillermo
    0.08
     алдын
    0.08
     skepticism
    0.08
     prevención
    0.08
     сезона
    0.08
    Act Density 0.001%

    No Known Activations