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

    Neuronpedia

    INDEX
    Explanations

    Telling stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    peace
    -0.08
     povol
    -0.07
     altı
    -0.07
     AsyncStorage
    -0.07
    _ATTACK
    -0.07
     materiál
    -0.06
    _four
    -0.06
    +++
    -0.06
     сообщ
    -0.06
    dto
    -0.06
    POSITIVE LOGITS
    жа
    0.06
    가요
    0.06
    ont
    0.06
    istics
    0.06
     synopsis
    0.06
    cliente
    0.06
     MA
    0.06
    471
    0.06
     결혼
    0.06
     考
    0.06
    Act Density 0.057%

    No Known Activations