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
     dock
    -0.07
     toys
    -0.06
    나
    -0.06
     births
    -0.06
     дерева
    -0.06
     heavy
    -0.06
     backwards
    -0.06
     childcare
    -0.06
    _weak
    -0.06
    -old
    -0.06
    POSITIVE LOGITS
    การศ
    0.07
     ал
    0.06
    Hex
    0.06
    'ai
    0.06
    endDate
    0.06
    �
    0.06
    _issue
    0.06
    رود
    0.06
    eterangan
    0.06
    ESH
    0.06
    Act Density 0.041%

    No Known Activations