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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <label
    -0.07
    Cat
    -0.07
    Were
    -0.06
    hours
    -0.06
     culmination
    -0.06
    Summary
    -0.06
     rebel
    -0.06
     time
    -0.06
    .wh
    -0.06
     CreateUser
    -0.06
    POSITIVE LOGITS
     bảo
    0.06
    isi
    0.06
     Hurricane
    0.06
     पस
    0.06
     labs
    0.06
     jMenuItem
    0.06
     ديسمبر
    0.06
     locks
    0.06
     pública
    0.06
    kke
    0.06
    Act Density 0.035%

    No Known Activations