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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     наруш
    -0.06
     getActivity
    -0.06
    ۶
    -0.06
    (web
    -0.06
     rz
    -0.06
    洞
    -0.06
     IX
    -0.06
    .helper
    -0.06
     liabilities
    -0.06
    弄
    -0.06
    POSITIVE LOGITS
    leader
    0.07
    ấc
    0.07
    _ttl
    0.06
    brero
    0.06
    ουν
    0.06
    πή
    0.06
    ồn
    0.06
    �
    0.06
    _ARGUMENT
    0.06
    arking
    0.06
    Act Density 0.147%

    No Known Activations