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
    19
    -0.08
     stead
    -0.08
    7
    -0.07
    59
    -0.07
     Rd
    -0.07
    д
    -0.07
     sd
    -0.07
     Erd
    -0.07
    75
    -0.07
    ánd
    -0.07
    POSITIVE LOGITS
     __
    0.14
    (__
    0.12
     $__
    0.09
    ::__
    0.09
     Jonathan
    0.09
     *__
    0.09
    #__
    0.09
    Jonathan
    0.08
    __,__
    0.08
    .__
    0.08
    Act Density 0.019%

    No Known Activations