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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     جریان
    -0.07
     Zag
    -0.07
     Lig
    -0.07
    BMW
    -0.06
    yonel
    -0.06
    Bed
    -0.06
    扱
    -0.06
    peaker
    -0.06
     yacht
    -0.06
    状
    -0.06
    POSITIVE LOGITS
     dependence
    0.08
     sqlalchemy
    0.07
    Climate
    0.07
    /@
    0.06
     Genetics
    0.06
     interview
    0.06
     secre
    0.06
    unch
    0.06
    -custom
    0.06
    �
    0.06
    Act Density 0.005%

    No Known Activations