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

    Neuronpedia

    INDEX
    Explanations

    individuals

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the word “individuals” (as in “households were made up of individuals”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     kariy
    -0.07
     поч
    -0.07
     نوشته
    -0.06
    .tools
    -0.06
     Ballet
    -0.06
     �
    -0.06
    _not
    -0.06
    -alert
    -0.06
     pot
    -0.06
    #endregion
    -0.06
    POSITIVE LOGITS
    descriptor
    0.07
    эф
    0.06
    entic
    0.06
    _ID
    0.06
     tolerate
    0.06
    Opp
    0.06
    adığı
    0.06
     iterable
    0.06
     Features
    0.06
     Decl
    0.06
    Act Density 0.000%

    No Known Activations