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

    Neuronpedia

    INDEX
    Explanations

    code/files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Held
    -0.08
     offen
    -0.08
    inar
    -0.07
    ("(
    -0.07
    onte
    -0.07
     terminated
    -0.07
    OTT
    -0.07
    üne
    -0.07
    pires
    -0.07
     linha
    -0.07
    POSITIVE LOGITS
     \↵
    0.12
    ้ส
    0.07
    ')):↵
    0.07
    "){
↵
    0.07
    ;\↵
    0.07
     dis
    0.06
     Abs
    0.06
    ,\↵
    0.06
    "\↵
    0.06
    NSDictionary
    0.06
    Act Density 0.006%

    No Known Activations