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

    Neuronpedia

    INDEX
    Explanations

    my little

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '"
    1.33
    '$
    1.21
     ResponseEntity
    1.14
    ="<%=
    1.14
     computerScore
    1.13
     spalle
    1.13
     moż
    1.13
    '.$
    1.10
     chất
    1.08
    ím
    1.06
    POSITIVE LOGITS
    न
    1.32
    फल
    1.31
    O
    1.23
    HOW
    1.18
    ه
    1.15
     beginners
    1.14
    𝙪
    1.12
    Universal
    1.11
    ेन
    1.11
     admirable
    1.10
    Act Density 0.000%

    No Known Activations