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

    Neuronpedia

    INDEX
    Explanations

    Good for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.73
    s
    1.25
     Azores
    1.17
    Status
    1.13
    ’;
    1.13
     seagulls
    1.07
     autobus
    1.02
    ের
    1.01
     tigre
    1.00
    </a>
    0.98
    POSITIVE LOGITS
     and
    1.55
     to
    1.26
     of
    1.20
    ва
    1.20
    ีย
    1.17
    ι
    1.15
     on
    1.13
    р
    1.10
    н
    1.09
    <0x98>
    1.07
    Act Density 0.116%

    No Known Activations