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

    Neuronpedia

    INDEX
    Explanations

    MY useState mtime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Azul
    0.85
     Vertex
    0.83
     Ibu
    0.81
     Selena
    0.80
     Paso
    0.77
     Loops
    0.76
     iced
    0.76
     ICE
    0.76
     Ét
    0.76
     Hub
    0.75
    POSITIVE LOGITS
    த்தகைய
    0.83
    culoskeletal
    0.83
    perspective
    0.82
    Deprecated
    0.82
    mbox
    0.81
    Deputy
    0.81
    idespread
    0.81
    <unused559>
    0.80
     불구하고
    0.79
    WaitFor
    0.78
    Act Density 2.310%

    No Known Activations