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

    Neuronpedia

    INDEX
    Explanations

    identity, existence, feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vests
    0.50
     advertisements
    0.46
     hamburgers
    0.46
     soybeans
    0.45
     necessitated
    0.43
     advertising
    0.43
     strollers
    0.41
     Cent
    0.40
     showrooms
    0.40
     Augusta
    0.40
    POSITIVE LOGITS
     stesso
    0.54
     stessa
    0.51
     włas
    0.51
     fratello
    0.51
    identité
    0.50
     чувства
    0.49
    Self
    0.49
    esistenza
    0.48
     스스로
    0.46
     když
    0.45
    Act Density 0.001%

    No Known Activations