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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     노
    -0.08
     UIView
    -0.07
     RELEASE
    -0.07
    .Java
    -0.07
    .Question
    -0.07
     düz
    -0.07
    mar
    -0.07
     jag
    -0.06
     Colorado
    -0.06
    usc
    -0.06
    POSITIVE LOGITS
          ↵      ↵
    0.08
    ]];↵
    0.07
    的关键
    0.07
    睐
    0.07
    []=$
    0.07
     lesb
    0.07
    둿
    0.07
    _feature
    0.07
    LDAP
    0.07
    照样
    0.07
    Act Density 0.004%

    No Known Activations