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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ounced
    -0.08
    issan
    -0.07
     boyunca
    -0.07
    .menu
    -0.07
     acidic
    -0.07
    uous
    -0.06
     scope
    -0.06
    	KEY
    -0.06
    enal
    -0.06
     communicated
    -0.06
    POSITIVE LOGITS
    만원
    0.06
     cố
    0.06
    ินการ
    0.06
     honeymoon
    0.06
     stringBy
    0.06
    そ
    0.06
    ('.')[
    0.06
    冊
    0.06
    _phys
    0.06
     tqdm
    0.06
    Act Density 0.000%

    No Known Activations