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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bound
    -0.06
     Ramadan
    -0.06
     Poison
    -0.06
     inbound
    -0.06
    pretty
    -0.06
     Avery
    -0.06
     suf
    -0.06
    .invalidate
    -0.06
    _ent
    -0.06
     alliance
    -0.06
    POSITIVE LOGITS
    ाड
    0.07
     roleId
    0.07
    Tiny
    0.07
     ALERT
    0.06
     jTable
    0.06
     لأن
    0.06
     """↵↵
    0.06
     fearing
    0.06
    Wik
    0.06
    TEX
    0.06
    Act Density 0.000%

    No Known Activations