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

    Neuronpedia

    INDEX
    Explanations

    available

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hugs
    -0.08
    有用的
    -0.07
     Hãy
    -0.07
     reserved
    -0.07
     Hands
    -0.07
     Shepard
    -0.07
     pessoa
    -0.07
     '-')
    -0.07
    .')
    -0.07
     Man
    -0.07
    POSITIVE LOGITS
     alleen
    0.08
     Router
    0.07
     TLC
    0.07
    📎
    0.07
    דל
    0.07
    很多朋友
    0.07
    Ⓐ
    0.07
    �
    0.06
    وني
    0.06
    Attr
    0.06
    Act Density 0.011%

    No Known Activations