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

    Neuronpedia

    INDEX
    Explanations

    benefits

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to employee pay and benefits (e.g., “compensation,” “packages,” “benefits”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     تج
    -0.07
    ETwitter
    -0.06
    osto
    -0.06
     Newtown
    -0.06
     towel
    -0.06
    958
    -0.06
    zzle
    -0.06
     ViewState
    -0.06
    ASON
    -0.06
     문서
    -0.06
    POSITIVE LOGITS
     features
    0.08
     Benefits
    0.07
    valor
    0.07
     feature
    0.07
     benefits
    0.07
    _dbg
    0.06
     WX
    0.06
     televizyon
    0.06
     Mobil
    0.06
     Percent
    0.06
    Act Density 0.005%

    No Known Activations