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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     value
    -0.08
    bon
    -0.08
     text
    -0.08
    目標
    -0.08
    OldData
    -0.07
     collaboration
    -0.07
     end
    -0.07
    情感
    -0.07
    简约
    -0.07
    	command
    -0.07
    POSITIVE LOGITS
    鬶
    0.08
    _peer
    0.07
     commuters
    0.07
    _BITS
    0.07
     doors
    0.07
    /files
    0.07
     fluent
    0.07
     tcb
    0.07
    חמש
    0.07
     neither
    0.07
    Act Density 0.024%

    No Known Activations