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

    Neuronpedia

    INDEX
    Explanations

    Code/URLs/Mixed strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ชนะ
    -0.07
     reordered
    -0.07
    Record
    -0.07
     complexes
    -0.07
     delightful
    -0.07
    vestment
    -0.07
    _REL
    -0.06
     beh
    -0.06
    Verse
    -0.06
     соверш
    -0.06
    POSITIVE LOGITS
     wraps
    0.07
    learning
    0.06
     saves
    0.06
    [][
    0.06
    (error
    0.06
            ↵        ↵
    0.05
    _MORE
    0.05
    foil
    0.05
    δό
    0.05
     mãe
    0.05
    Act Density 0.290%

    No Known Activations