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

    Neuronpedia

    INDEX
    Explanations

    closed due to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onces
    0.55
     Jimenez
    0.54
     initialise
    0.52
    érences
    0.51
    ir
    0.50
    ó
    0.50
    áték
    0.49
    hent
    0.49
    âteaux
    0.49
     Fernandez
    0.49
    POSITIVE LOGITS
    .
    0.52
    Pat
    0.48
    4
    0.47
    9
    0.47
    3
    0.46
    R
    0.45
    Razor
    0.45
    Patent
    0.44
    </b>
    0.44
    खर
    0.42
    Act Density 0.001%

    No Known Activations