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

    Neuronpedia

    INDEX
    Explanations

    suffering, evil

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases referring to human suffering, pain, loss, or injustice.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    タ
    -0.07
    段
    -0.06
     belle
    -0.06
     find
    -0.06
    ided
    -0.06
    лор
    -0.06
    .met
    -0.06
    .streaming
    -0.06
     intend
    -0.06
     podstat
    -0.06
    POSITIVE LOGITS
     fellow
    0.07
    variably
    0.07
    DeltaTime
    0.06
     gerek
    0.06
     реєстра
    0.06
    ظٹ
    0.06
     Neg
    0.06
    流量
    0.06
    .addActionListener
    0.06
     selfie
    0.06
    Act Density 0.006%

    No Known Activations