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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ncias
    -0.07
     terminator
    -0.07
    )i
    -0.06
    -da
    -0.06
    .then
    -0.06
     Immediate
    -0.06
     ons
    -0.06
     Bij
    -0.06
     donde
    -0.06
     lagi
    -0.06
    POSITIVE LOGITS
     좋아
    0.07
    墓
    0.06
     peş
    0.06
    elic
    0.06
     hackers
    0.06
    papers
    0.06
    .ToUpper
    0.06
     jeopard
    0.06
     Do
    0.06
     Offline
    0.06
    Act Density 0.000%

    No Known Activations