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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -be
    -0.07
     Nathan
    -0.07
    .File
    -0.06
     nause
    -0.06
    prime
    -0.06
     File
    -0.06
    dom
    -0.06
    合同
    -0.06
    ِك
    -0.06
    	iVar
    -0.06
    POSITIVE LOGITS
    ┐
    0.07
    -----------↵
    0.06
     pob
    0.06
     тот
    0.06
    (Contact
    0.06
    RowAnimation
    0.06
    .NORTH
    0.06
    _IPV
    0.06
    �
    0.06
     쉽
    0.06
    Act Density 0.011%

    No Known Activations