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

    Neuronpedia

    INDEX
    Explanations

    science and software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     affinities
    -0.75
    ftagPool
    -0.73
     betweenstory
    -0.68
     propOrder
    -0.68
     attenuated
    -0.66
    WebControls
    -0.65
     labored
    -0.63
     scaffolds
    -0.60
    jspx
    -0.59
    enterOuterAlt
    -0.56
    POSITIVE LOGITS
    ized
    0.55
    OGND
    0.55
     least
    0.52
    ization
    0.52
    Portail
    0.52
    naio
    0.52
    tidaknya
    0.51
     turn
    0.50
    itamos
    0.50
    orum
    0.49
    Act Density 1.616%

    No Known Activations