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

    Neuronpedia

    INDEX
    Explanations

    mal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سد
    -0.07
    asurable
    -0.07
     Alternatively
    -0.07
    mnop
    -0.06
     composer
    -0.06
     preview
    -0.06
     все
    -0.06
    pieces
    -0.06
    ABLE
    -0.06
     Sith
    -0.06
    POSITIVE LOGITS
     stag
    0.07
    	end
    0.06
     έκ
    0.06
    참
    0.06
    香港
    0.06
    
    0.06
    .Ma
    0.06
     Survivor
    0.06
    _door
    0.06
    (bottom
    0.06
    Act Density 0.226%

    No Known Activations