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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     success
    -0.07
     bash
    -0.06
     Fiesta
    -0.06
     mention
    -0.06
     Dan
    -0.06
    Stay
    -0.06
    ())
↵
    -0.06
     Reports
    -0.06
    34
    -0.06
    Trap
    -0.06
    POSITIVE LOGITS
    rabbit
    0.07
     serr
    0.07
    Specifier
    0.06
     �
    0.06
     کودکان
    0.06
    :'',
    0.06
     cid
    0.06
     цель
    0.06
     resolutions
    0.06
    _OID
    0.06
    Act Density 0.026%

    No Known Activations