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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ौड
    -0.06
     forgot
    -0.06
     trapped
    -0.06
    ，加
    -0.06
    aycast
    -0.06
    _STORAGE
    -0.05
    -0.05
    ー�
    -0.05
     procrast
    -0.05
    /dataTables
    -0.05
    POSITIVE LOGITS
    ving
    0.07
    ños
    0.07
     hypertension
    0.07
     Exam
    0.07
    \↵
    0.07
     myst
    0.06
     warning
    0.06
    TLS
    0.06
    /en
    0.06
    /wiki
    0.06
    Act Density 0.001%

    No Known Activations