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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     philippines
    -0.06
     IDX
    -0.06
     Nun
    -0.06
    	UPROPERTY
    -0.06
    axios
    -0.06
     indx
    -0.06
     здесь
    -0.06
     tun
    -0.06
     forgiving
    -0.06
     right
    -0.06
    POSITIVE LOGITS
    ラク
    0.06
     confirmed
    0.06
     {↵↵↵
    0.06
    Samples
    0.06
     Ahmet
    0.06
     ран
    0.06
    '}}>↵
    0.06
    ossip
    0.06
    κι
    0.06
    akis
    0.06
    Act Density 0.014%

    No Known Activations