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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }$/
    -0.06
    ocache
    -0.06
    MOV
    -0.06
     angry
    -0.06
    ************************
    -0.06
    ovali
    -0.06
     FOLLOW
    -0.06
    _FEED
    -0.06
     congr
    -0.06
    活
    -0.06
    POSITIVE LOGITS
     �
    0.07
    状况
    0.07
    ise
    0.07
    (pos
    0.06
     disrupting
    0.06
     '?
    0.06
     �
    0.06
     ford
    0.06
     Som
    0.06
     ilgi
    0.06
    Act Density 0.000%

    No Known Activations