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

    Neuronpedia

    INDEX
    Explanations

    Code/software revisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    458
    -0.07
     orchestra
    -0.07
    (Logger
    -0.06
     volcan
    -0.06
     recursive
    -0.06
    pired
    -0.06
     PJ
    -0.06
     mpg
    -0.06
    ContentAlignment
    -0.06
     jeopard
    -0.06
    POSITIVE LOGITS
    iais
    0.07
     filtro
    0.06
     Zip
    0.06
     appreh
    0.06
     ue
    0.06
    gons
    0.06
    usuarios
    0.06
    侧
    0.06
    utoff
    0.06
    oppins
    0.06
    Act Density 0.015%

    No Known Activations