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

    Neuronpedia

    INDEX
    Explanations

    Code layouts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，比
    -0.07
     名前
    -0.07
    ดา
    -0.07
    PropertyDescriptor
    -0.06
    ียนบ
    -0.06
     محل
    -0.06
     FEC
    -0.06
     ven
    -0.06
     частини
    -0.06
     nga
    -0.06
    POSITIVE LOGITS
    ños
    0.07
    icon
    0.06
    ifa
    0.06
     Dialog
    0.06
    _out
    0.06
    346
    0.06
    /root
    0.06
     japan
    0.06
     Batch
    0.06
     scrimmage
    0.06
    Act Density 0.000%

    No Known Activations