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

    Neuronpedia

    INDEX
    Explanations

    latitude and longitude coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.93
     de
    0.92
    K
    0.90
     Health
    0.89
     existential
    0.85
     voir
    0.84
     Routes
    0.82
     e
    0.82
     (
    0.82
     social
    0.81
    POSITIVE LOGITS
    চৈত
    1.02
     вспо
    0.91
    тное
    0.91
     কাহারও
    0.91
    ClrBit
    0.91
    bcc
    0.89
     spinors
    0.89
    sion
    0.89
    deling
    0.88
    BufOffset
    0.88
    Act Density 0.000%

    No Known Activations