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

    Neuronpedia

    INDEX
    Explanations

    phosph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ipher
    -0.08
    ()(
    -0.06
    _rep
    -0.06
    ilitary
    -0.06
     bamboo
    -0.06
     Spare
    -0.06
    _recv
    -0.06
     burden
    -0.06
    509
    -0.06
     Paperback
    -0.06
    POSITIVE LOGITS
    ोजन
    0.07
    _verified
    0.07
     Verification
    0.07
    PAL
    0.06
    _listing
    0.06
    사항
    0.06
     Trie
    0.06
    �
    0.06
    Thinking
    0.06
    lied
    0.06
    Act Density 0.006%

    No Known Activations