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

    Neuronpedia

    INDEX
    Explanations

    code/data files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cherry
    -0.07
     clearing
    -0.07
     marrying
    -0.07
     Исп
    -0.07
     infiltr
    -0.06
     tavern
    -0.06
     Bil
    -0.06
     หม
    -0.06
     NFS
    -0.06
     striker
    -0.06
    POSITIVE LOGITS
    .UN
    0.07
     pseudo
    0.06
     대전
    0.06
    scribers
    0.06
    sharp
    0.06
    meler
    0.06
    對
    0.06
     getPassword
    0.06
    /***************************************************************************↵
    0.06
    /community
    0.05
    Act Density 0.011%

    No Known Activations