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

    Neuronpedia

    INDEX
    Explanations

    similar cases, properties, problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    痪
    0.38
    Bor
    0.37
     conducción
    0.37
    磕
    0.37
     Pamela
    0.36
    resel
    0.36
     नकल
    0.36
     limpio
    0.35
     conduz
    0.35
    бие
    0.35
    POSITIVE LOGITS
     websites
    0.47
     magic
    0.40
     assets
    0.39
     routines
    0.39
    magic
    0.38
     openings
    0.38
     features
    0.37
     hypotheses
    0.37
     characters
    0.37
     apps
    0.37
    Act Density 0.000%

    No Known Activations