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
    owitz
    -0.09
    ite
    -0.08
     Wei
    -0.08
    avi
    -0.08
     putchar
    -0.07
    288
    -0.07
    ichte
    -0.07
     où
    -0.07
    _encoder
    -0.07
    iving
    -0.07
    POSITIVE LOGITS
    #
    0.13
     #
    0.12
    :#
    0.10
     (#
    0.09
     '#
    0.09
    (#
    0.09
    nd
    0.09
    �
    0.08
    ="#
    0.08
    ลล
    0.08
    Act Density 0.098%

    No Known Activations