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

    Neuronpedia

    INDEX
    Explanations

    specifications and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    miy
    0.88
    atching
    0.87
    atch
    0.87
    Backup
    0.86
    inių
    0.86
    áticos
    0.84
    itized
    0.83
    pidos
    0.83
    ības
    0.82
    oot
    0.81
    POSITIVE LOGITS
    ↵
    0.88
    ?
    0.87
    ↵↵
    0.86
     refers
    0.83
     The
    0.82
     |
    0.80
    )
    0.80
    ;
    0.78
    ↵↵↵
    0.78
     [
    0.77
    Act Density 0.675%

    No Known Activations