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

    Neuronpedia

    INDEX
    Explanations

    selection

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of evolutionary processes, especially occurrences of “selection.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ucwords
    -0.06
     pacientes
    -0.06
     timestamp
    -0.06
     terminator
    -0.06
     emissions
    -0.06
     orbs
    -0.06
    武器
    -0.06
     frag
    -0.05
     strftime
    -0.05
     rand
    -0.05
    POSITIVE LOGITS
     산업
    0.07
    ريل
    0.07
    alien
    0.07
    適用
    0.07
     '',
    0.07
    वर
    0.06
     плит
    0.06
    .surname
    0.06
    then
    0.06
    agine
    0.06
    Act Density 0.006%

    No Known Activations