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

    Neuronpedia

    INDEX
    Explanations

    effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _user
    -0.07
     runway
    -0.06
    ta
    -0.06
    	u
    -0.06
     dut
    -0.06
     Eddie
    -0.06
     ratt
    -0.06
    @Data
    -0.06
     improvis
    -0.06
     outing
    -0.06
    POSITIVE LOGITS
     совершенно
    0.08
     DESCRIPTION
    0.07
     craftsm
    0.06
    ;:;:;:;:
    0.06
    خواست
    0.06
    ']:
    0.06
     обеспе
    0.06
    役
    0.06
     ><?
    0.06
     عامل
    0.06
    Act Density 0.035%

    No Known Activations