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

    Neuronpedia

    INDEX
    Explanations

    transactions, policies, collectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jurid
    0.41
     aure
    0.39
     mars
    0.37
     strony
    0.36
     ambiguities
    0.36
     onyx
    0.36
     acog
    0.35
     qué
    0.35
     karet
    0.35
     maya
    0.34
    POSITIVE LOGITS
    WA
    0.39
    Love
    0.37
     Love
    0.37
    MP
    0.36
    OM
    0.36
    MS
    0.35
     Conv
    0.35
    Conv
    0.34
    AM
    0.33
    წყვე
    0.33
    Act Density 0.001%

    No Known Activations