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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovy
    -0.07
     nm
    -0.07
    =message
    -0.07
    .sell
    -0.07
    ...)↵
    -0.07
     reference
    -0.07
     references
    -0.06
    \_
    -0.06
    _GEN
    -0.06
     jed
    -0.06
    POSITIVE LOGITS
    _Err
    0.07
    ("
    0.07
     cautious
    0.07
    ekten
    0.06
     اجازه
    0.06
     öyle
    0.06
    Dave
    0.06
     yerde
    0.06
    Editing
    0.06
     العالم
    0.06
    Act Density 0.016%

    No Known Activations