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

    Neuronpedia

    INDEX
    Explanations

    nl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crippling
    -0.07
    arkers
    -0.07
     Voj
    -0.06
    _opacity
    -0.06
     Peaks
    -0.06
    weights
    -0.06
     Mer
    -0.06
     coefficients
    -0.06
    	make
    -0.06
    	win
    -0.06
    POSITIVE LOGITS
    HF
    0.07
    nl
    0.07
    l
    0.07
    NL
    0.07
     Dutch
    0.07
    BAR
    0.07
    応
    0.07
    (pl
    0.07
     Relay
    0.07
    ελ
    0.06
    Act Density 0.005%

    No Known Activations