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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rif
    -0.06
     Sha
    -0.06
    _SI
    -0.06
    :Set
    -0.06
    谅
    -0.06
    飕
    -0.06
    .waitFor
    -0.06
    _<
    -0.06
    .every
    -0.06
     Wood
    -0.06
    POSITIVE LOGITS
     enclave
    0.08
    行星
    0.08
    仍然
    0.07
     donor
    0.07
    慷慨
    0.07
     activités
    0.07
    (answer
    0.07
    (res
    0.07
     recycle
    0.07
     how
    0.07
    Act Density 0.006%

    No Known Activations