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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AutoSize
    -0.07
     Assistance
    -0.06
     bounce
    -0.06
     colonial
    -0.06
     Francesco
    -0.06
    icients
    -0.06
     forgiveness
    -0.06
     corrid
    -0.06
    .Cl
    -0.05
    .AspNet
    -0.05
    POSITIVE LOGITS
    较
    0.07
     мире
    0.07
    /[
    0.07
    llum
    0.06
     harmon
    0.06
    axon
    0.06
    紧
    0.06
     inhabit
    0.06
    {name
    0.06
     yoğun
    0.06
    Act Density 0.000%

    No Known Activations