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

    Neuronpedia

    INDEX
    Explanations

    final stage or part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.51
     corneal
    0.45
     هیڅ
    0.45
    சிரியர்
    0.44
    steacher
    0.44
    சிக
    0.44
    taught
    0.43
     cuenta
    0.43
     updateUser
    0.43
    ح
    0.43
    POSITIVE LOGITS
    )，
    0.45
     acres
    0.43
     JavaBeans
    0.43
     Acres
    0.42
     τις
    0.41
     Equip
    0.41
    动物
    0.41
     rays
    0.41
     Galleries
    0.41
     ανθρώ
    0.41
    Act Density 0.000%

    No Known Activations