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

    Neuronpedia

    INDEX
    Explanations

    even if / platform team

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ίας
    0.48
     Nú
    0.45
    ğu
    0.44
     Doctors
    0.44
    drav
    0.43
    뽑
    0.43
     výraz
    0.43
    ivamente
    0.42
     выбран
    0.42
    nome
    0.42
    POSITIVE LOGITS
    Metadata
    0.52
    raits
    0.46
    Singleton
    0.45
     fluffy
    0.44
    helps
    0.44
     पांडे
    0.44
     frees
    0.42
     fluff
    0.42
    Outgoing
    0.42
     moonlight
    0.42
    Act Density 0.001%

    No Known Activations