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

    Neuronpedia

    INDEX
    Explanations

    Latin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comps
    -0.08
     unh
    -0.07
     ROW
    -0.07
    .attach
    -0.06
    )]↵↵
    -0.06
     stret
    -0.06
     bec
    -0.06
     Jos
    -0.06
     içer
    -0.06
    izr
    -0.06
    POSITIVE LOGITS
    resse
    0.07
    -East
    0.07
     calculus
    0.06
    _ACCOUNT
    0.06
    seys
    0.06
    JsonObject
    0.06
     Appeals
    0.06
    (),'
    0.06
     Stocks
    0.06
     WARRANTIES
    0.06
    Act Density 0.023%

    No Known Activations