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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    appointment
    -0.06
     gettimeofday
    -0.06
    ital
    -0.06
    okens
    -0.06
     regards
    -0.06
    uler
    -0.06
    ushi
    -0.05
    due
    -0.05
    time
    -0.05
     bel
    -0.05
    POSITIVE LOGITS
     reminis
    0.08
    .Ap
    0.07
     ذ
    0.07
    _VOID
    0.07
    	LP
    0.07
     Wolf
    0.07
    Од
    0.07
     AT
    0.07
    교회
    0.06
    บอก
    0.06
    Act Density 0.067%

    No Known Activations