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

    Neuronpedia

    INDEX
    Explanations

    helplines and phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alphanumeric
    0.20
     hexadecimal
    0.20
    ()/
    0.19
    ৫০
    0.19
     რომელი
    0.19
    (%
    0.18
    ABCDEFGHIJKLMNOP
    0.18
     DHCP
    0.18
     Identifier
    0.18
     SNMP
    0.18
    POSITIVE LOGITS
    গ
    0.21
    ड
    0.20
    у
    0.20
    ра
    0.19
    פ
    0.19
    <unused1726>
    0.19
    а
    0.19
    и
    0.19
    ј
    0.18
    ка
    0.18
    Act Density 0.186%

    No Known Activations