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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _temperature
    -0.08
    -route
    -0.07
     Bernie
    -0.07
     racer
    -0.07
    roy
    -0.07
    Passwords
    -0.07
     gearbox
    -0.07
    िजल
    -0.06
    oca
    -0.06
     heating
    -0.06
    POSITIVE LOGITS
    //--------------------------------------------------------------↵
    0.07
     suggest
    0.07
    '=>$
    0.06
    [J
    0.06
     abstract
    0.06
     itk
    0.06
     Mö
    0.06
     tweeted
    0.06
    Ngh
    0.06
     suggested
    0.06
    Act Density 0.008%

    No Known Activations