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

    Neuronpedia

    INDEX
    Explanations

    fitting text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MR
    0.51
     Significant
    0.50
     Built
    0.47
     wall
    0.46
     Considerable
    0.46
     Careers
    0.46
    ist
    0.45
     mild
    0.45
     considerable
    0.44
     substantial
    0.44
    POSITIVE LOGITS
     играет
    0.60
    нів
    0.58
     sách
    0.53
    นคร
    0.52
    па
    0.51
    atilde
    0.50
     hrá
    0.50
     письма
    0.50
    <0x94>
    0.50
    чені
    0.49
    Act Density 0.000%

    No Known Activations