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

    Neuronpedia

    INDEX
    Explanations

    conspiracies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Task
    -0.07
    .YELLOW
    -0.07
     наві
    -0.07
    	field
    -0.07
     pit
    -0.06
    _json
    -0.06
     норм
    -0.06
    çak
    -0.06
    ец
    -0.06
    Wave
    -0.06
    POSITIVE LOGITS
    -cloud
    0.07
    ceiver
    0.07
     Agencies
    0.06
    ,E
    0.06
     implanted
    0.06
               ↵
    0.06
     Stainless
    0.06
    /Set
    0.06
    alta
    0.06
     WITHOUT
    0.06
    Act Density 0.079%

    No Known Activations