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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blocking
    -0.06
    設備
    -0.06
    干
    -0.06
    AMA
    -0.06
    .loaded
    -0.06
    ائف
    -0.06
     cheered
    -0.06
     shifting
    -0.06
     schnell
    -0.06
     Exclude
    -0.06
    POSITIVE LOGITS
     ordinarily
    0.07
    REG
    0.07
    tain
    0.06
    agency
    0.06
    '}}>↵
    0.06
    YES
    0.06
     hind
    0.06
     vrch
    0.06
     komm
    0.06
    lara
    0.06
    Act Density 0.000%

    No Known Activations