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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     educated
    -0.07
     randomly
    -0.06
    共和国
    -0.06
     Terrain
    -0.06
     balloon
    -0.06
     Candid
    -0.06
    デル
    -0.06
     Bride
    -0.06
     Province
    -0.06
     branches
    -0.06
    POSITIVE LOGITS
    beginTransaction
    0.06
    �a
    0.06
    след
    0.06
    '")↵
    0.06
    erde
    0.06
    _PE
    0.06
    岩
    0.06
    .SetToolTip
    0.06
    .free
    0.06
    @\
    0.06
    Act Density 0.124%

    No Known Activations