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

    Neuronpedia

    INDEX
    Explanations

    APIs and rate limits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recorded
    -0.08
     Grants
    -0.07
    ratings
    -0.07
     Backup
    -0.06
    Public
    -0.06
    GetValue
    -0.06
     вред
    -0.06
    Weak
    -0.06
     �
    -0.06
     bö
    -0.06
    POSITIVE LOGITS
     róż
    0.07
    _RG
    0.07
     consequ
    0.06
     attravers
    0.06
     canv
    0.06
     MCC
    0.06
     kang
    0.06
     htons
    0.06
     sophistication
    0.06
    :NSUTF
    0.06
    Act Density 0.072%

    No Known Activations