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

    Neuronpedia

    INDEX
    Explanations

    colors and light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ammonium
    0.87
     Apprentices
    0.82
     Ceramic
    0.71
     Semiconductor
    0.71
     Astronomy
    0.70
     Engineered
    0.70
     Original
    0.69
     Formulation
    0.69
     Antim
    0.68
     Cornerstone
    0.67
    POSITIVE LOGITS
    ocar
    0.83
    cil
    0.78
     stok
    0.74
    igues
    0.74
    occa
    0.73
    ♌
    0.72
    otricha
    0.71
    𝓰
    0.71
    0.70
    érieurs
    0.70
    Act Density 0.009%

    No Known Activations