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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scarlet
    -0.08
     Velvet
    -0.07
    Flo
    -0.07
    owych
    -0.07
     propio
    -0.06
    ใกล
    -0.06
     fab
    -0.06
    した
    -0.06
    Inventory
    -0.06
    k
    -0.06
    POSITIVE LOGITS
    “We
    0.06
    (()=>{↵
    0.06
    _|
    0.06
    .shortcuts
    0.06
    нес
    0.06
     questioning
    0.06
    "We
    0.06
    (evt
    0.06
    risk
    0.06
    				↵				↵
    0.06
    Act Density 0.006%

    No Known Activations