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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    进入到
    -0.07
    aneously
    -0.07
    poly
    -0.07
    logging
    -0.07
    BorderStyle
    -0.07
    ndata
    -0.07
    turned
    -0.07
    ☂
    -0.07
    frag
    -0.07
    .ne
    -0.07
    POSITIVE LOGITS
     analsex
    0.08
     Holt
    0.07
     Ис
    0.07
    对他
    0.07
    截至目前
    0.07
    ;.
    0.07
    遗产
    0.07
     depos
    0.06
     Schmidt
    0.06
     arthritis
    0.06
    Act Density 0.004%

    No Known Activations