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

    Neuronpedia

    INDEX
    Explanations

    self-improvement and career

    np_max-act · gemini-2.0-flash

    The neuron responds to nouns that name abstract personal or emotional concepts (e.g. “relationship,” “strength,” “imagination”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    lemma
    -0.07
    "Our
    -0.07
    _socket
    -0.07
     your
    -0.07
    私の
    -0.07
    allocation
    -0.07
     my
    -0.06
    .include
    -0.06
     American
    -0.06
    's
    -0.06
    POSITIVE LOGITS
     ����
    0.06
     مسئ
    0.06
     fi
    0.06
    userinfo
    0.06
    ROL
    0.06
     kosten
    0.06
    Crystal
    0.06
     Extras
    0.06
     radi
    0.06
    para
    0.06
    Act Density 0.085%

    No Known Activations