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
    (%
    -0.07
    TITLE
    -0.07
    露出
    -0.06
     VERIFY
    -0.06
    _ticks
    -0.06
    TAIL
    -0.06
     �
    -0.06
     Ron
    -0.06
    یت
    -0.06
     developing
    -0.06
    POSITIVE LOGITS
    ossa
    0.06
    pcs
    0.06
     Reference
    0.06
     стос
    0.06
    ogr
    0.06
     Nos
    0.06
     allegation
    0.06
     ACL
    0.06
     shl
    0.06
    Argentina
    0.06
    Act Density 0.268%

    No Known Activations