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

    Neuronpedia

    INDEX
    Explanations

    code/logs/references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    玳
    -0.07
    .devices
    -0.07
     multif
    -0.07
    亚太
    -0.07
     allocation
    -0.07
     measles
    -0.07
     fly
    -0.07
    梅
    -0.06
    Compiled
    -0.06
     Hogwarts
    -0.06
    POSITIVE LOGITS
    -refresh
    0.07
    ”
    0.07
    되면
    0.07
    передач
    0.07
    endors
    0.06
    packed
    0.06
    สงคราม
    0.06
    -turned
    0.06
    _presence
    0.06
    /stretch
    0.06
    Act Density 0.323%

    No Known Activations