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

    Neuronpedia

    INDEX
    Explanations

    Debug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opacity
    -0.07
     lucrative
    -0.06
     mug
    -0.06
     bar
    -0.06
    74
    -0.06
    NU
    -0.06
     chuyển
    -0.06
     stool
    -0.06
    Fortunately
    -0.06
     commands
    -0.06
    POSITIVE LOGITS
    ++++++++++++++++++++++++++++++++
    0.07
    ــــــــ
    0.07
     हव
    0.06
     đẹp
    0.06
    　r
    0.06
     різні
    0.06
     Báo
    0.06
     freel
    0.06
    .innerHeight
    0.06
     neler
    0.06
    Act Density 0.006%

    No Known Activations