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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fre
    -0.07
    .Upload
    -0.06
     crap
    -0.06
     io
    -0.06
     fwrite
    -0.06
    Checker
    -0.06
     Biol
    -0.06
    	project
    -0.06
    報告
    -0.06
    ]↵↵↵↵
    -0.06
    POSITIVE LOGITS
     vliv
    0.07
     Plaza
    0.07
    engan
    0.07
     Professionals
    0.07
     incarcerated
    0.06
     opted
    0.06
    =img
    0.06
    plier
    0.06
    opp
    0.06
    andFilterWhere
    0.06
    Act Density 0.025%

    No Known Activations