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

    Neuronpedia

    INDEX
    Explanations

    AI powered and patients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pubescens
    0.50
    aterials
    0.43
    ക
    0.43
    azy
    0.43
    answered
    0.42
    âh
    0.40
    eties
    0.40
    ethylamine
    0.40
    cine
    0.39
    alia
    0.39
    POSITIVE LOGITS
    0.42
     thumb
    0.38
     menyes
    0.38
     Servi
    0.37
     mering
    0.37
     March
    0.37
     Cooper
    0.36
    </body>
    0.36
     riff
    0.36
     onu
    0.36
    Act Density 0.001%

    No Known Activations