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

    Neuronpedia

    INDEX
    Explanations

    Describing towns/villages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <!
    -0.07
     knee
    -0.07
    ow
    -0.07
    UGH
    -0.06
    ("`
    -0.06
    ció
    -0.06
    ugh
    -0.06
    plotlib
    -0.06
    497
    -0.06
    icus
    -0.06
    POSITIVE LOGITS
     THANK
    0.07
     beforeSend
    0.06
    ávací
    0.06
     опред
    0.06
    finding
    0.06
    ควบค
    0.06
     výbě
    0.06
    aturdays
    0.06
     gimm
    0.06
     Stripe
    0.06
    Act Density 0.022%

    No Known Activations