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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stras
    -0.07
     deb
    -0.07
     Casc
    -0.06
    717
    -0.06
     Hunts
    -0.06
     music
    -0.06
     matrices
    -0.06
     Interfaces
    -0.06
     Emm
    -0.06
     clos
    -0.06
    POSITIVE LOGITS
    abilirsiniz
    0.07
    _fh
    0.07
     Harmon
    0.06
    izin
    0.06
    =sum
    0.06
     AUTHOR
    0.06
    paginator
    0.06
    نه
    0.06
    SEG
    0.06
    RCT
    0.06
    Act Density 0.057%

    No Known Activations